Master the future of process automation. Nin is an incredibly powerful open- source platform that enables you to integrate APIs and orchestrate intelligent workflows without the usual coding headaches. This course from Maronei will guide you from the foundational concepts of nodes and architecture to deploying advanced real world systems. You'll master essential skills like connecting various services, configuring API keys, and handling complex data flows. Also, the course

goes into cutting edge AI integration, teaching you how to build advanced retrieval automated generation or rag agents and coordinate multi-agent systems. By the end, you'll be able to automate sophisticated business processes, giving you a competitive edge in DevOps, AI, and data engineering. Automation is no longer just a buzz word. It's reshaping how teams work, collaborate, and scale. At the heart of this revolution is Nen, an open-source extensible automation platform that lets

you connect APIs, orchestrate workflows, and even build intelligent AI agents with ease. From sending simple automated emails to creating advanced multi-agent rack system, NAN empowers you to streamline operations, boost productivity, and unlock whole new levels of innovation. Welcome to NATE zero to hero course by Cookcloud. I'm Maronei and together we'll go from beginner to advanc as we explore how to build powerful automations with NIET. Whether you're a DevOps engineer, an AI

enthusiast or someone from a nontechnical background looking to automate real world processes, this course is designed for you. We begin with the introduction section where you get familiar with Naden itself, the playground environment and the code structure. You'll also understand the objectives so you know exactly how each step builds towards your automation skill set. Next in the foundations of edit end we'll cover the essentials understanding notes inputs and outputs

and we'll talk about data types in editn and finally how wful run under the hood using an endn's default logic. You'll also configure API keys for services like OpenAI, Anthropic, and CodeLab Keyspaces so you're ready to integrate AI into your workflows right from the beginning. From there, we jump into hands-on AI agent workflows. This is where the fun begins. You'll build your first email AI agent to drop responses on autopilot. Create a multi-agent research workflow that pulls knowledge

from tools like proplexity and open AAI, turning hours of work into minutes. Explore the HTTP request node. your key to working with APIs from web scraping, data fetching or calling other external agentic tools. Experiment with creative workflows from text to image, text to video, and even image to video automations using bleeding edge models like Google's V3 and Cand. And yes, we'll even build a Slack workflow that lets AI reply to your co-workers and your managers on your behalf. So while

you're sipping coffee, Edit end is already answering questions for you, aka doing your job. In the optional setup section, we'll explore how we can self-host nit with Docker and use Ola as your local LLM, as well as hosting on AWS EC2 in our playground environments. This flexibility means you'll know how to run NAD in a way that matches your scale, budget, and preferences. Then we'll dive into rag agents retrieval augmented generation. You'll learn how vector databases like pine cone gives

workflows memories and contexts. Together, we'll build a customer sport rag agent, the kind of workflow that real businesses use to provide intelligent contextaware support. We'll also explore MCPs and see how they compare to traditional workflows, unlocking new possibilities for reusability and scalability. In the multi-wordflow advanced build, we'll combine multiple agents into enterprise style system, showcasing how subflows let you manage complexity without chaos.

Finally, we'll cover retries, error handling, best practices, and how to leverage the editor workflow template marketplace to accelerate your builds. By the end of this course, you'll have learned how to build a practical real world automations like Slack AI agents, multi-agent research workflows, multimodal automations, customer support rag agents, and advanced multiworkflow orchestration systems. And along the way, you'll engage with hands-on labs designed to reinforce learning by doing

so. So, every concept becomes second nature. At Cook Cloud, we believe in learning by building. And you'll be part of a vibrant community where you can share insights, ask questions, and grow together. So, ready to move from zero to hero with Nin. Let's dive in and unlock the full potential of workflow automation.

Hey there and welcome. In this section, we're going to walk through the foundations of NIDN, an open source workflow automation tool that makes connecting apps and services simple. Here's what we'll cover. We're going to do a quick introduction of NIDN and its building blocks nodes. And then we're going to explore AI agent architecture and API flow. And later on, we'll showcase how it works in an email to select use case. I'll also show you how input formats and expressions work in

NIDN. And finally, we're going to talk about how Nadn handles data types. Let's dive in. All right. So, what is NN? Well, NN is short for notation, and it's a free open-source workflow automation tool. Think of it like a universal connector. You can link different apps, services, and even AI agents together without writing tons of custom code. The magic happens through something called nodes. You set up workflows visually step by step and edit end handles all the data passing in between. In add

workflow with a trigger event that you define like a new email arriving or a web being called and then there's the action nodes that do the work like send an email, interact with an LLM or call an API. By chaining these together, you can turn everyday manual tasks into smooth automated flows. Now, let's look at AI agents inside Nitn. Just like any other node, an AI agent within a workflow will be triggered by an event or a trigger node. And there are three important elements that make this node

an AI agent. Namely, the LLM, which is the brain that powers the agent. And this could be open AI, plot or llama, or any LLMs that you hook up to it. And of course, the way you connect them would be through an API access token. And then there's a context window memory which gives the agent context of the workflow interaction and the tool that you can use to complete tasks like Gmail, web scrapers, or any tools that you connect to it. And of course, you connect that

node to an output into either the next node or just as a chat response. Here's how it works. Your workflow grabs some user input, say a simple chat trigger. The agent thinks about that input and based on what you've asked, whether it's sending an email or just having a quick chat, it decides if it needs to call tools like Gmail or any other tools that you hook into it through the APIs. Then it pass the output back to your workflow. So it's input going into the

agent, deciding whether to use the tools or not, and then passing out the output. And that's how you get intelligence mixed into your automations. And here's how that looks inside N itself. A chat trigger kicks things off. An AI engine agent node hooked up to GPT does the thinking. A Gmail node can send messages and an output node fires the result straight to Slack. It's the same logic but now mapped visually into the workflow editor. Now by default addin run nodes sequentially.

So it's trigger to the next node to the next note and the next node. If the nodes are connected in a line, everything runs in order until the workflow finishes without skipping any nodes. Which means if along the line one of the nodes fail, it will cause the workflow to error out. In this case, you'll see that there's a Tavly tool attached to the AI agent. And because it is only a tool hooked up to the agent, it is optional for the workflow to run this. And it depends on whether the AI

agent decides that it is appropriate to call on this tool based on the instructions received. And in the middle, you'll see that there's a if conditional loop. And this just ensures that the workflow doesn't error out when it doesn't get the result in time from external APIs. But we'll get to the details of that in the next few sections. But workflows don't always go in a straight line. You can brush them out. So one input might trigger two parts. Maybe one branch post to Slack

and the other goes to Gmail. In this case, each branch runs independently. It'll run the top one first and then the second one sequentially, giving you two actions from the same trigger. AI agents need memory. And there are two main flavors. We have the context memory, which is a short-term memory inside the AI's prompt. It's great for chat history and to get the AI to stay in context. And it is a difference between a stateless and a stateful response from the AI agent. And we'll run some

examples to show you the difference in practice later on. And then there's a vector database or documents rack memory, which is long-term searchable memory. Here your documents get stored as embeddings and the agent retrieves only what's relevant when answering. This is a knowledge source outside of LLM's training data. So simple memory is leveraged for context and continuity to make sure that the AI agent stays context and rag is used for scale and accuracy.

Every node in addit has an input and an output. In the input panel, you see the payload data that the node is receiving from the previous node. So in this case, it is a chat message received from the user because the previous node was a chat trigger node and the output is basically the response of the LLMs or the AI agent and the data structure ranges from very simple with one variable or multivariable with different ranges of data types and additional informations. But it is worth noting

that every node has an input and an output data and the output data of this node will be the input payload of the next node and that's how the logic strings the entire workflow together. So this makes it super easy to see what's flowing through your workflow and data doesn't always look the same. So in ended end there are three main types of data that you'll see in the input and output panel. So the first one is schema which is a defined data structure and the second one is a table format with

rows and columns handy for spreadsheets and then of course there's that underlying JSON which is the most common structured and flexible way to show the data and sometimes you get other types like binary for files and images. It's worth noting that these are different representations of the same data. When you configure a node, you can type in a fixed value like a static string or you can use expression which pulls dynamic data from earlier nodes. Expressions allow your workflow to adapt to

real-time inputs instead of being hardcoded in. And the cool thing about N&N is the fact that you can drag and drop the variables or parameters into the fields within their low code UI. Now let's talk data types. The basic building blocks inside NN. So in Naden there are many five different data types which is strings, numbers, boolean, arrays and objects. So strings are like text for example hello world. Numbers as it suggests are values like 42, 3.14 or -100. Booleans

are simply true or false statements and arrays are essentially lists like a list of numbers or a list of names. And objects are structured data like what you see in the example which contains the user credentials including name and email. Objects can even nest and you often access them with dot paths and expressions and knowing the differences and mastering these makes everything else click. One of the coolest things about NN is the community nodes. These are extra connectors built by users

extending NN way beyond the official nodes. So, if you don't see a built-in integration for your favorite tool, check the community first. Chances are someone's already made it. Once you're in the workflow, the very first step that you want to do is to introduce a trigger node into the workflow. The trigger node, as it name suggests, is a node that's going to trigger your entire workflow when the event that is dependent on it is triggered. So let's go ahead and hit the

plus button on the top right hand side here and it will generate a list of options or possible trigger nodes that you can start your workflow with. Now the most simplest one is the trigger manually node which triggers every time you click on it. But in this case what we're going to choose is an on chat message trigger node. And once you click on a note there usually are going to be some fields that you need to configure. But in this case, because it's a simple chat message received node,

what happens is that a terminal will pop up here where you can actually interact with the chat node. In this case, I'm just going to type in hello to populate it with the relevant data. Now, a quick way for you to differentiate between a trigger node and a regular node is by the lightning icon here on the left that you see. Now let's open up a chat message receive trigger node to see how the data is populated within the note. As this is a trigger note, you only have

an output data from the node and you do not have the input data. Now if we covered in the previous sections, there are three types of representation of the same data that you'll be able to see within each nodes. In this case, the underlying data format is JSON with three different information that's contained within the payload. Now the first information is the session ID which identifies a session of the chat and then we have the action message which in this case is send message

because we're sending message through the chat input and there's a chat input content which in this case was what I typed in which is hello. Now when you toggle over to the table section what you'll see is the same data representation in a table format. As you can see this session ID, the send message action at the chat input which is hello. Now if you toggle over to schema, you can see the same representation of the data in a schema format which makes it easy for you to drag and drop to the

next node when you need to. Now let's go back to the workflow. Once that first node has been set, the second node that you want to hit is the AI agent node. Now in this case I'm going to click AI. I'm going to select AI agent. Now when you open up a node the data from the output of the previous node automatically populates the input of the AI agent node. And this is true for any types of nodes when you connect it to the previous nodes. The output payload of the previous node is going to be the

input of the current node. Now in this case because the AI agent is already connected to the chat trigger we can leave this as a connected chat trigger node in terms of the prompt or the user message it is correctly identifying as JSON chat input which is the content here which is hello and you can see that hello is represented here as the actual value of the variables. Now with every AI agent node, what you need to pay attention to are three key elements that make this node an AI

agent. So the first is of course the LLM. So LLMs are the lash language models basically is the brain behind the AI agent note. Now in this case there are long list of options of LLM that you can choose from and each of these are good for specific use cases. In this case, we're going to choose an OpenAI chat model as the model that we want to hit. Now, I already have an OpenAI account set up here, but I'll show you how to connect your OpenAI account or your OpenAI API keys pretty easily. In this

case, just hit the dropown and click on create new credential. And in this field, what you want to do is to populate it with the API key that you can either obtain from CodeCloud Keyspace or the OpenAI developer platform. We'll cover how you can get the OpenAI API key from CodeCloud Keyspace or the OpenAI developer platform in another section. In this case, you can also fill in your organizational ID or it could be optional. Now, once you've key in your API key, you can hit save.

And once you've connected your OpenAI account, what you can do now is to pick from a list of GPT models that OpenAI has to offer. In this case, we're going to pick GPT for Mini because it's intelligent enough for most use cases. Now, moving on, the second element that we don't want to attach to the AI Asian node, it's a memory node. And what does memory mean for the AI agent? Well, this is basically the persistent memory that tells the AI agent or gives the AI agent the context

that it requires from previous conversation. And I'm going to show you very quickly what happens when an AI agent has no memory versus when it does. Now, in this case, we're going to type in hello, my name is Mark.

And when I type that in, the agent now access this open AI LLM chat model to infer the information and respond to me by saying, "Hello, Mark. How can I assist you today?" Okay. And in the next thread, what I'm going to ask is, "What is my name?" So, since I've just told him that my name is Mark, it should be able to tell me what my name is. But as you can see in the output, and let me just move this up. It says, "I'm sorry, but I don't have access to personal information about users unless

you shared it with me in this conversation. How can I assist you today?" So, as you can see, it has no memory context of what I just said, which is my name is Mark, even though I just typed it in a minute ago. So, now let's attach a memory bank. In this case, we're going to choose a simple memory. And as you might have noticed, there are various options of different types of memories that you can attach to the AI agent. But the simplest way uh to get started is to click on

simple memory and choose that as the option. And there are a couple fields that come with the simple memory as well. But in this case, because our connected trigger node is a chat trigger node, we can leave this as that. And the context window length basically means how many past interactions to model that the memory will retain. So in this case, we're going to keep it as five and then it will remember five different iterations or five previous iterations of the conversation that you

have with the agent. So we're going to leave it as that. Now you might notice that now the AI agent node is showing a yellow highlight around it with a triangular icon and that means some changes has been made to the AI agent and in this case the change was the memory node being attached to the AI engine and showing that so that you can run the workflow again so that the data can be repopulated. In this case I will do the same thing. I will say hello my name is Mark.

As you can see it's doing the same operation but this time it's actually dipping into the simple memory and now are able to store that information. So I'm going to ask it again what is my name? And this time as you can see it says your name is Mark. How can I help you today Mark? So now it retains the memory of the information that I've just given it a minute ago. And you might notice the terminal in the middle here are basically the logs of what's going on within the node. So in

this case, what happens was a chat message was received. The data was passed on to the AI agent and the AI agent is zipping into the simple memory to check what my name is or the information that was given earlier and then using the open AI chat model to return the information.

Now that the chat model and the simple memory has been set, the third thing that we want to attach the AI agent to or provide the AI agent with is the email tool. So now there are various tools that you can attach. But in this case, because we want the AI agent to be an email agent, we want to attach the Gmail note. when you're attaching a Gmail note, you need to set up your Gmail credentials to be associated to the account. I already have my Gmail account set up here.

But if you haven't set up your Gmail account before, it is pretty easy. The way you would do it is to create a new credential. And if you're using an cloud, you would sign in with Google as an ooth to recommended way. or if you're using a self-posting method, you might want to choose a service account and fill in the necessary information that's required to set up the Gmail account properly.

Now, as you can see, there are a couple fields to configure here. The first one is tool description. We're going to leave this as set automatically because we're going to let the AI model determine whether they want to use Gmail or not. The second field is a resource. In this case, we want to do message because we want to be able to send message through the Gmail tool. And the operation of course is send. And so you can see there are other options as well. So when we

attach a Gmail tool oftent times it doesn't mean that we just want to send an email. It can also do many other operations such as reply a specific type of email or mark an email as read or unread or delete an email or many other options. Now going into the information of the email itself, there are a couple of information that we need to pass to the AI agent for it to determine what to do with the email. So first of course who is the recipient of the email. Now because this is going to change

depending on your input. Now remember because your input is going to be in natural language whether that's English or any other languages this is going to be different every time. So what you want to do in that case is to let the model define what the email address is. That way whatever your input is, the model is going to infer the information and try to extract the necessary information that you think is correct for the email address and the subject itself is also going to

be determined by the model. We're going to let it do that and we can do that by clicking the same blue button here to let it determine the subject. When it comes to email type, in this case, we want to choose a text email just for simplicity. HTML is very good when it comes to imagerich type of email. So, if you're looking to attach any image or any thumbnail and you want it to be aesthetically formatted within the email, then you would choose HTML. But in this case, we're going to go

ahead with text. And then on message, we want to choose determine by model as well because that way we're going to let the AI determine what kind of body of the message that is going to attach. Okay. So now the three elements have been configured. We want to go back to the AI agent node to specify certain prompts. But before we do that, there are a couple of things that I think it's worth highlighting. As you probably have noticed, with every single field that comes within a

particular node, there is a fix and expression toggle here. Now, I just want to highlight the difference between fix and expression. So, because the AI agent node is connected to the chat trigger node, we've left this as connected to chat trigger node. But what you can do is actually to define what the input is. So, when we click on define below, we specify exactly what kind of input that goes into the prompt or user message prompt. So in this case I can drag and drop the

chat input and it will fill it up as an expression. Now the difference between fix and expression a fixed format is basically a natural language format with which you can tell the AI agent a specific but permanent definition of what the user message is. So for example, if I were to put the user message as please send an email, this is going to be the input for every single run that I execute of this workflow. And that's not ideal because we want the AI agent to be able to get

the information dynamically depending on my input. So in the first run, I might put what is my name instead of please send an email. So we want the prompt or the user message to change together with my prompt. So how do we do that? That's when we toggle into expression. And what happens is we can now drag the chat input variable in this case and simply drop them into the prompt user message. And what happens is as you can see it creates an expression in this case a

JavaScript expression of the variables of the chat input. Meanwhile the actual value of the variable is dictated here which is what is my name question mark. So, as you can see on each separate run of the workflow, it's going to populate the information based on my input instead of a prefix input if I were to choose a fixed format. I hope that explains the difference between fix and expression. Well, and in this case, the next thing I want to do is to go to options and under add option,

I'll go to the dropdown and click on system message. Now for those of you who are not sure the difference between a system message and a user message, the user message is a set of instructions or input that comes directly from the user. Meanwhile, the system message describes the core function of this particular model. So in this case, what I want to tell it is that you are a helpful email assistant which helps craft effective and succinct email based on users

instruction. You also help with sending the email by using attach email tool when asked. Now this is a very simple system prompt and I would suggest that for a more effective system promp that you go to chatgpt or llm of your choice to prompt engineer an effective system prompt for a particular AI agent. That's what I would do in a production scenario. But in this case, because we're just running a quick demo, we're going to stick with a simple one just so

that you understand the principle behind it. Cool. Now that we have the system prompt defined as well as the user prom variable in place, we can now take it for a spin. Now in this case, what I want I want to do is to say the same thing, which is hello, my name is Mark. And as you can see, it's accessing both the open AI chat model and a simple memory to store the information, but it's not necessarily using the Gmail tool. And the reason for that is because

I did not specifically ask the agent to send any email just yet. So as you can see from the response, hello again Mark, what would you like to do today? Is the response which is also the same response here. Now I would say I would like to send an email to my boss at maronei@codecloud.com which is not my real boss's email address is actually my email address because I don't want to necessarily send my boss a test email about the upcoming marketing meeting on 26th of August 2025.

So, I'll hit that. As you can see, it's not necessarily using the Gmail tool straight away because it is intelligent enough to know that it needs a little bit more information. So, it says, "Sure, what would you like the subject and the message of the email to be?" So in this case, because I'm too lazy to come up with the subject and email, please, please come up with it yourself. Okay. So I'm going to say that and it gives you a draft of the email. So in this case, it says subject

upcoming marketing meeting on August 26, 2025. Dear boss's name, I hope this message finds you well. I wanted to remind you about the upcoming marketing meeting scheduled for the 26th of August 2025. Let me just blow this up. We will be discussing our strategies and plans for the upcoming quarter. Please let me know if there are any specific topics you would like to address during the meeting. Looking forward to your input, Mark. And I would like to make changes

because it says, as you've noticed, my boss's name. So, let's say my boss's name is Moonshot. Okay, so now it registers that and gives me a new draft. Dear Moonshot, I hope this message finds you well about the upcoming marketing meeting. Da da da. And then it says, shall I go ahead and send this email to moonshotaronecloud.com? Again, this is not his email. This is my email because I don't actually want this to be the email that sent to him. So I would say yes, please go ahead and send it.

So once I've confirmed that, what happens is, as you can see, the AI agent is now accessing the Gmail tool to send the email to actually in this case my own email. So let's take a look what it looks like in my inbox. Now this is the email that's been sent to me. As you can see, because the Gmail account over here is connected to my email or my Gmail, which is marone@codecloud.com, it is essentially sending from marone@codpow.com to me. That is this in the content of

course. Dear Moonshot, I hope this message finds you well. Wanted to remind you of the upcoming marketing meeting schedule for 26th of August 2025. So, everything looks nice. I can almost send this directly to Moonshot. But what I want to do is as you can see at the end of it, it says this email was sent automatically by NAND. So that's not ideal because Moonshot will find out that I'm actually automating this email. So what I want to do is go back to the NAND workflow and go to the Gmail tool

and scroll down to options. Under add options, I'm going to click on the dropown and click on append edit and attribution. And what I want to do now is to toggle this off. In this case, it will actually stop attaching the message of the end attribution in the email. So in this case, what you can do when you want to execute a step is to hit the play button on top of the note so that you don't have to rerun the entire workflow. So let's just click on that. Okay. So now that that's done, I want to

take a minute to explain some of the little functions here that you see and what they do. The first one is the play button which is the execute step button. So this button is super useful when you want to run the node without essentially running the entire workflow again. So if you change anything within the AI agent node and you only want to run the AI agent node again, you would hit this button. It will only run the node here. The power button as you can see here is

to deactivate the node because this is the only node basically that does any processing in this workflow. But as your workflow grows more complex, you might have five or six branches of nodes. And some of them, if they're not in use, you might want to deactivate. So if you click on deactivate, what happens is it's going to say that the node has been deactivated. And basically, the workflow is not going to work for any processes that go through this particular node.

And we're going to reactivate that again. And of course, the bin icon is to delete the entire node together. Now another very useful function in within any is a pin. Now if you were to open up the node and go to the top right hand corner you can see that there's an option to pin the data. Now this is super useful because now you don't have to key in or populate this particular node with new data all the time. And this is extremely valuable when you're running a workflow that uses API

tokens or might cost you for every run of the workflow. So to avoid running the workflow again and again and using or activating the API token, what you can do instead is to pin the data to the node so that every single demo run or every single trial run is using the data that's already been populated. So once I pin this data, every single run of the chat input is only going to say yes until I push it to production. Now once you've done all this, this doesn't mean that your workflow has been

pushed to production. So the way you would push to production is to toggle the activate workflow option right at the top here. And when you do that, it's going to give you a warning message to say you can now make calls to your production chat URL. Okay. So click on got it. And there you go. Your workflow is now in production. You do not have to click on execute workflow to run the workflow. And every single message that it received is going to run the way you set up the workflow.

So just to try that out, I'm going to use hello. I'm going to have to pick on pin and send. And there you go. It's a new response. Now, of course, this workflow isn't very useful because the only way you can interact with the AI agent is through the terminal here. Now, how can we provide a publicly available terminal so that more than one users or people who don't have access to your end to end workflow can also use this AI agent? Well, if you open up your chat note, what you can see is that

there is a make chat publicly available option. And what you want to do is just to toggle that. In this case, it's going to give you a URL that you can copy and open up. And you might have to wait for a couple seconds for it to stand up, but once you do, this is a page that is publicly available as long as you pick the option to make the chat publicly available and you can access the AI agent as any user would. Cool. And as you can see, there are a couple options here

that you can configure if you want to include an authentication or if you want to have an initial message that is crafted or customized to your needs. But in this case, we're going to keep it simple because in this section, we just want to run through the principles of how to create your first AI agent workflow on NN. And I hope that has been helpful. And just before we go, you might notice that there are three options to choose from from here, which is the editor version where we have been

actually building the NDN workflow on which obviously as the name suggests where you edit all the nodes and configure all the nodes in the workflow, but also the executions button where you can check out the logs of the executions. As you can see, it gives you the date, the time, and the type of execution. The one with the beaker icons are test executions or basically the workflow runs that we did when it was in demo mode. And once I push it to production, it is an actual execution to the

workflow in production. And one of the things you can do once your workflow is in production is also to copy the data that's been populated during the execution for troubleshooting purposes. So if you click on copy to editor what happens is your editor will now show the information that is derived during the execution of that production workflow. So remember in the chat we said hello and here it is the chat input content is hello

and similarly the AI agent response is hello how can I assist you today which is the response that we got from the live chat. Now, this is a very useful option because it just makes your troubleshooting as well as your iteration a lot easier as you build or modify workflow in production. So, I hope you were able to follow through on the demo of how to build your first AI agent workflow on Edn. In the next section, we're going to give you a lab where you build the exact same AI

agent within that particular lab and see for yourself if you're able to create an AI agent that crafts email and sends it on your behalf. This course comes with free labs that could be accessed right in your browser. So, you don't need to set anything up yourselves or use your credit cards. The labs are challenge based, meaning we give you a challenge and ask you to solve it. Use the link in the description below to sign up for free labs on codecloud. I'll now walk

you through your first lab. In the upcoming labs, you're going to experience hands-on building AI agents on NAD environments. And in doing so, you're going to need an API access to the LLMs of your choice. And in order to do that, you need the API keys. And there are a couple ways to get your API keys. Naturally, you can go to OpenAI to get your OpenAI API keys or platforms like Open Routers on which you can obtain API keys of several different models. But those platforms require

payment information before you're able to get the API keys even if you're just trying out. So, one of the things that we've done here at CodeCloud is we've created the CodeCloud code key. And what it is, it is the all-in-one AI playground where you can get the API keys to the following LLMs of your choice. And at the time of this recording, models like GPT40, GPT4.1, cross on 4, Gemini 2.5, and Grog 3 are available through the code key playgrounds. And the code key playground

is available on various different subscription plans, but you get the most access with AI plans and the business plan. Now, if you were to go to this page, which is codecloud.com/ai-playground/code key with the right access, you can hit launch now and click on start playground and you'll be led to a dashboard where you can essentially create and grab your API keys by selecting the models as well as the different types of ways or methods with which you can access the

LLM model. Now, in this case, I'm going to do an example of how to call a GPT 4.1 model through a code key on your NDN environment. So, there are two ways to do that. The most straightforward way is to go to your end workflow. I'm going to start the trigger node with a chat trigger because I want to be able to communicate with the agent and I'm going to just populate the node with something like hello. And we're going to introduce a second node which is the OpenAI node.

In this case, we're going to choose a message and model node. And what we want to do here is to create a new credential. And we call this code key demo for example. And what you want to do under the base URL, replace this base URL with the base URL that you can obtain from the code key page. Copy that. Go back to the workflow and paste the base URL in. And of course for the API key, we're going to take the API key here and we're just going to paste it in and we're going to

hit save. And you'll see that sometimes depending on the version of the NA cloud that you're in, this red bar might pop up. Don't worry too much about it because I'm going to show you how you can keep using it even if the red bar shows up. And this is just simply because the UI itself is not designed for users to patch in their base URL themselves like that. And sometimes that causes some form of incompatibility which causes the red bar to show up. In this case, under model, what we want to

do is we're just going to define it by ID because we're going to type in the name of the model ourselves because this is not going to be the models that are in the list from OpenAI. And if you were to try to grab it from the list, it's not going to load at all. So, we're going to hit buy ID and we're going to manually type in open AI/GPT-4.1.

And that's the model that we want to call here. As you can see, is GBT-4.1. And with that model, we're going to transfer or rather drop in the chat input variable. So, that essentially everything is connected. And we're not going to add any tool at this point because we're just going to hit execute step. And as you can see it is coming up with an output or response to the chat input which is hello. It says hello how can I help you today. So with that simple setup you can now chat with the

model here. For example I can ask why is the color of the sea blue and as you can see under the chat the output is here in the response the sea appears blue primarily because of the way water absorbs and scatters sunlight. Um, and that's the response for that. Now, that's one way to gain access to a LLM model through code key. The other way to do that is to call a HTTP node. So, I'm just going to add another trigger node here. And this time, I'm going to select

trigger manually. I'm going to move this down right here. I'm going to add the HTTP request node. And if you were to go back to the code key documentation, as you can see, we can actually toggle this to the curl command and I'm going to copy the entire chunk here of the curl command and go back to my workflow. I'm going to hit import curl. I'm going to paste the entire thing and it's a post API call to this particular endpoint URL. And of course there's some authentication here which is already

prefilled actually because I pasted the entire curl command. Ideally we want to set up the authentication on the headers but we'll go over that part later on in the next section. But in this case without doing too much what I want to do is I want to just hit execute step and there you go. So under JSON body you can see that there is a preconfigured content which is in a single sentence. Why should someone choose codecloud over other platforms to learn DevOps? That is

the user prompt that has been prepopulated there. So you can essentially replace this with some other variables that you receive from the input. Like for example, if it's a chat trigger that's connected, you can drag those chat trigger as the user input and drop it in here to replace this whole line. But here I just want to show you that it is responding to the user prom as someone should choose code cloud over other platforms to learn devops because it offers highly interactive hands-on

labs and real world scenario based exercises that accelerate practical skills development far beyond traditional video based courses. So cool. These are the two ways that you can gain access to the LLM API keys via KOI. And as I've shown earlier, you can choose from these various models right now. For the next few sections, this might come in handy for you. Otherwise, you can always go to the actual provider like OpenAI or Anthropic to get those API keys. I'll see you in the next one.

So I want to run through the differences between running your instance on end cloud versus the lab playground that we have on the codecloud course. Now the first thing you'll notice as you go into the lab is that you still have to provide your email and your first name last name credentials as well as a password in the instance. And don't worry this is not saved anywhere. So you don't actually have to save the credential and the password somewhere. You can use different emails and

password for each of these instances. So once that's filled in you can hit next. And there's going to be a series of onboarding questions here which you don't need to fill. So you can hit get started and in the same way for the paid features information you can just skip and there you go. Now you're in the admin dashboard that is very similar to the end cloud environment. However, there's still some nuances and some differences as we go into the workflow. So here what we're going to do is we're

going to click start from scratch. And the very first workflow that you're going to build is the email AI agent. And the first trigger to that is a chat trigger. And I'm going to speed through this cuz this is very similar to the workflow that we've done. But I want to just show you quickly the differences of using the KCloud keyspace as well as the OpenAI API key. So if you're using the KCloud keyspace, what you want to do when you select your model, for example,

in this case, I'm just going to select the OpenAI chat model. And what I want to do is to follow the instruction in the left hand bar right here. And you see that there's a link to Code Key. I'm going to just hit that URL. I'm going to hit launch now. and it's going to lead me to this dashboard right here. I'm going to click start playground and there we go. So, this is the dashboard on CodeCloud Keyspace. And what I want to pick is the OpenAI GPT 4.1. And in

this case, I'm going to just copy the API key here. I'm going to go back to my workflow. And here, I'm going to hit create credential. And I'm going to paste the same exact API key. I'm going to skip the organization ID. And for the base URL, I want to make sure that I'm replacing this with the base URL that I obtained from the KCL keyspace. Go back to my lab and paste the base URL right here. Okay, so I'm going to hit save right now. As you can see, it says

connection tested successfully. However, there's a couple of things I want to point out here cuz if you pick from list, as you can see, the list doesn't really match the known models of GPT. This is because it's not really working based on the UI that's been built. So if you try to run it based on the chat ID or chat model that we've selected, I'm just going to run a hello message here. It's going to go to the AI agent, but it's going to error out. So what you

need to do is go into the chat model and instead of picking from list, you want to go by ID and as suggested from the instruction on the left hand bar here, you want to copy the OpenAI/GPT-4.1. Just copy that and paste it all word for word. And let's do a test run again. And this time it should actually be able to access the appropriate model. So that's if you're using the CCloud keyspace API keys. Now what I want to point out is the difference between this and using

the OpenAI API key is that it's much more straightforward when you use OpenAI API keys. So to show you the difference, what I'm going to do here is I'm going to create another new credential and I'm going to call it OpenAI account 2. This time I'm going to head over to platform.opai.com. And what I want to do is head over to API key section. I'm going to create a new secret key in and then email integration. I'm going to hit create secret key and I'm going to copy the API

key and head back to my lab. I'm going to paste the API key and leave the base URL as is and I'm going to hit save. So there you go. So connection tested successfully. And the difference is instead of by ID, I can now just pick from the list and it should load up the correct list of models that I might possibly want to use. So for example, if I choose GPT 4.1, it's just going to be that. And we're going to run this node again. And as you can see, it's calling

the correct model right here. Okay. So the next thing I want to point out is when you add your Gmail note on the next workflow or Google tool for that matter the difference between doing that in our labs versus edit cloud is that on edit and cloud you often see when you create a new credential with Gmail that you can actually have a button which you can sign in directly using your Google account if your browser happens to be a Google Chrome browser. However, with the

labs what you need to do when you create a new credential is you actually need to connect it with the o method. So what you want to do is you want to head over to console.cloud cloud.google.com. And the first thing you want to do is create a new project. And for the new project, I'm going to name it Enit in email app. All right. So, I'm going to leave this as no organization. I'm going to hit create. And it's going to take a couple seconds to create a project. And

once that's done, I'm going to select the project. And as you can see, it says end email app project. And the very first thing I want to activate is I want to go to Gmail API. So what I'm doing right now is I'm creating a project because that's how Google recognizes each of these ooth access that we're giving it. But the way the security works is you need to enable the particular tool that you want to use within the project. So in this case I want to use Gmail. So I want to make

sure I enable the Gmail API. All right. Once that's enabled, I want to head over to OOTH consent screen. And right now there's no OOTH consent that's set up. So I'm going to just hit get started. And in this case, I'm going to have to call it an app name as well. So I'm just going to say it is an email app. Okay. User support email. Going to put this. And we're going to select external. And by the way, each of these steps is documented on the left hand side panel of the lab. So you don't have to

memorize any of these. But we're going to go to next. And under contact information, just going to put my email here. And once you're done, just hit continue. and create. So, just before we go, I just want to go to audience and I want to add a test user here, which is an email that you're going to use to send out basically the emails that you want the agent to send out. So, in this case, it's maroneia atcookcloud.com. We're going to save that. And lastly, we're almost there. We're going to go to

API and services again, and this time we're going to go to credentials. And what we want to do is to hit create credentials with OOTH client ID and application type we want to choose web application and under name you want to name it Canadian email oath client and then we're going to add the authorized redirect URLs which we can obtain from our lab. So, going back into the lab here, you see that this is the oath redirect URL and we're going to copy this and we're going to head back and

just fill this in and we're going to hit create. As you can see, we now have the client ID and client secret to the app that we just created. So, we're going to copy this and head back to client ID. Paste it in. Client secret. Copy that. Paste in the client secret. And you'll see now that there is a sign in with Google button that pops up. So, what you want to do is just hit that and a Google login popup will show and then you just want to correctly select the email

address and you'll say that Google hasn't verified this app. But because you're the one who created it, you know it's safe. So, we're just going to hit continue and we're going to select all because we want to have the agent be able to do all these actions with our Gmail. So, we're going to hit continue now. And as you can see, it says connection successful and we're good to go. So, just wait a couple seconds here within the labs and it's just going to load up. And there you go. I already

have my credentials set up here and we just want to run an execute step to show you that everything is working. So in the workflow you'll see that we've chosen to define all of this by the model. So we're going to let the AI agent define this and we're going to start chatting and say hi can you send an email to.com to just say hello. All right so we're going to hit this. So as you can see now the workflow has run and it's actually sent an email to my Gmail. So let me

take a look and there you go. It says hello Mercury just want to say hello best regards. Okay. So obviously it's not very sophisticated because actually in the AI agent we didn't even specify any system prom. So the whole point is just to show you the main difference between running the environment on N cloud and within our playgrounds specifically covering the part where code key is being used as well as when you're going to access any Google tools, Gmail, Google sheets and stuff like

that. You do need to go to your Google Cloud Console to set up the project, the app, and the OOTH clients in order to access Google services with the workflow. And as you explore Nit in the course, you're going to realize that there's going to be some differences between running edit cloud and edit within your own self-hosted environment. For example, the availability of community notes, supported versions, and a few other features that might only be available on edit cloud. So if you're

facing any issues any part of that build, just keep in mind that it might be because you're using a self-hosted version or a lab hosted version from CodeCloud. And it's not necessarily a limiting issue. There's always a workar around for that. It's just something to keep in mind about. I want to take a minute to go through the different types of authentication that we can make in our approaches when we make HTTP request nodes and the corresponding API calls. Now, as you've seen in the previous

section, the HTTP request node is a very convenient way for us to replicate an API call without configuring everything. And it's especially useful when we can just go to an API documentation and hit the import curl, essentially import the entire curl command. Now, as you've seen in the previous example, there are a few ways that we can configure the authentication method in these API calls. Now, most of the API calls are going to be header authentication. As

you can see in this section after I've imported the curl, it automatically configures the header section and populate it with the name and the value format of the API keys for authorization. Now you can do it this way or you can actually set up a credential type here. Now I want to explain the difference between the two. So there are two main reasons why you would want to do it this way by setting up a credential type. The number one reason is it's just super convenient

because the moment you have set this up with the header off credential, you can just pick from the list of credential you've created in the next upcoming nodes or even in another workflow. And this is especially useful when you have an API call that has a post and a get so you don't have to set it up again in next node. Now the second reason why you want to do it this way is for security reasons because setting up credential type allows you to approach the authentication without hard coding the

API key into the parameters and this is just a better practice to ensure security especially when you're sharing the workflow on the project with multiple team members and individuals and all your credentials is going to be stored under credential tab you can have an overview of the list of credentials that you've set up and of course you can delete it or you can recon configure it from this page. Now, that's it about authentication. I'll see you in the next section. So, in this section, we're

going to run through how to set up your Google Cloud Console and connect it to your NDN. That way, you're going to be able to start using the Google notes such as Google Drive, Gmail, Google Sheet, Google Docs, and a variety of others without setting it up over and over again. So, the note that we're going to start with here is the Google Drive node. And the reason why we're choosing this is because the way to connect it is going to be similar across all nodes. In fact, once you've

connected it once, everything else would just be a simple matter of enabling APIs through your Google Cloud console. So, in this case, under credential, what I want to do is to create a new credential. And in order to get your client ID and client secret, where you want to go is to go to console.cloud.google.com. And depending on whether you've worked with Google Cloud before, and by the way, if you have and you already know how to get connected with Nitnen, then

feel free to skip over to the next section. But your page might look slightly different from what I'm seeing right now. But in any case, where you want to go is on the top leftand corner. You want to pick the project here. And again, as you can see, I already have one set up, but I'm going to set up another one. Click on new project. And I'm going to call it end demo KKK. And under location, I'm going to pick new organization here. And I'm going to hit create. And there you go. It's creating

a Niden demo KKK project. I'm going to click on select project and I'm going to pull up the left hand sidebar here. Where I want to go is under APIs and services. I want to go to the OOTH content screen and nothing set up yet. So I'm going to hit get started. So app information and then demo KKK. I'm going to call it the same name for the app and click that as the email. And for the audience, you have the choice of internal and external depending on whether you have your

Google workspace set up. Internal is only available if you have a Google workspace. But in this case, I'm going to hit external. And contact information. I'm going to use the same here. Hit next. Check on that and hit continue. And we can go on create. All right. So the next step, I want to hit the create oath client. And what essentially we're doing here is that we're creating a project even though it's not a real project. Google just likes to use this as a structure to

identify and keep track of the oath clients that people create. So essentially where what we want to do here is we want to pick application type web application and in the name we're going to choose nan demo kk again and we're going to leave this as is and we're going to add an authorize to redirect URLs here and where we're going to get this URL is from our workflow or run our credential here and click on copy and go back to our Google console. Paste that and hit

create. So now we have the client ID. We're going to copy that. We're going to go back to our workflow here. So client ID, we're going to paste that in. Go back to our console here. And what we want to do is to add a client secret. And we're just going to copy that. Go back to our work and paste the client secret in. So just before we hit sign in with Google here, which will activate the connection, we're going to head back to our Google Cloud Console and go to

branding and scroll down to authorize domains. So in this case, what we want to do, we want to add an authorized domain, which is editn.cloud. We're going to hit save. And the other thing we're going to do is to type in drive in the search bar and hit Google Drive API because we want to enable this API here. And of course, we're going to have to enable Gmail API as well as sheet and docs as well. But in this case, we're going to just enable the drive and we're going to try it out. And

once you've enabled the drive API, the last thing you want to do is head over to audience and essentially publish the app. All right, we're going to confirm that and head back to our workflow here and hit sign in with Google. and you're going to be redirected to a Google signin page and you're going to have to click your email and it's going to say Google hasn't verified this app, but it's okay because it's you who's launching this. And once you've done that, there's going

to be a couple permissions that you need to run on the credentials. So, we're going to select all of these and we're going to hit continue. And there you go. Connection successful. So, we're going to head back to our workflow here. As you can see, account is connected. And once you've connected your account, you'll be able to see the list of folders that you have on your drive. So in this case there's only one folder in my drive which is KK test folder. So I'm

going to hit that and essentially we can watch for file created for example right so anytime a file is uploaded it's going to trigger this. So we're going to hit fetch test event. I didn't upload any file so it says no data with the current filter. So this is the folder right here. I'm going to open that up. I'm going to upload a dummy file, which is an S SOP file. And there we go. So, we're going to go back to workflow here and rerun the test again. And as you can

see, now it's fetching the data of the file that has been uploaded. So, cool. For the other nodes such as Google Sheet, Google Docs, what you need to do is just to go back to your Google Cloud Console and essentially enable your APIs by typing in the Google notes or the Google tool that you want to use. For example, in this case, Google Sheets API. You want to enable that and you can go back and connect that on your edit end and you're good to go. All right, I'll see you in the next section. In

this section, we're going to build a simple workflow of an AI research agent that goes out to the internet and search for the latest AI news and send it across to you via email and at the same time log those particular headlines so that the next day the workflow is going to check against the logs so that it doesn't repeat the same headlines. And this is a workflow that's going to be super useful in this day and age when AI news pops up every other day. So this is what the entire workflow will

look like. We start off with a scheduled trigger node which is preset to a certain time of each day. Let's say 9:00 a.m. And then this goes to a Perplexity search. So as you know, Perplexity is one of the leading search AI agent out there. And we're going to use that to search the latest news or headlines that is pertaining to AI development. And then we're going to kick the output to a checking agent. And what this does is it dips into the Google sheet which locks

all the previous headlines of the news to make sure that it doesn't repeat the same headlines. And after that, it's going to send a summary of this AI news and send it out to the intended recipient via Gmail. And the final step is going to log those headlines to make sure that the AI agent stays up to date with those logs. Now, let's build it together. The first thing you want to do is introduce the trigger note, which in this case is a scheduled trigger note to kickstart the

entire workflow. With the schedule trigger node, you can choose what the trigger intervals that you want. In this case, it could be days, hours, minutes, or seconds or even longer than that. As we want this workflow to kickstart every single day, we want to choose days. And the days in between triggers, we want to keep that as one because we want it to send out at every single day. The trigger hour is something that we can choose based on preference. And in this

case, we're going to choose 9:00 a.m. because we like the news to be delivered to us in the morning. And we're going to keep the trigger at minute zero. And we're going to hit execute step just to populate the data. And there you go. We have set our first trigger node. Now the second note that we want to introduce here is a perplexity note. And usually when it comes to using thirdparty tools, what you typically do is go to the API documentation of the third party tools

and make a HTTP request towards those API endpoints. However, in this case, Perplexity has a native node that lives within NN which you can choose from and is easy to use. In this case, I'm going to choose message model note from Propexity. And I already have my Propexity account credential set up. But I'm just going to walk you through very quickly how you can easily do that. So in this case, you're going to pick the dropown and click on create new credential. And as

you can see is as simple as keying in the API key from Plexity. What you could do is go to Plexity.ai and in the main dashboard, go to your account and click on settings. And under settings, if you look at the lefth hand side tab, you want to hit API keys. And your API keys page may not look like this because you do need to set up your API billing before being able to access these keys. You can easily do that by heading to API billing and putting in your credit card information and topping

out the credits at a minimum of $5. But in this case, I've already gone ahead and do so. What we can do here is to hit the create key button and it's going to create an API key ready for us to copy. Now head back to the workflow and copy the API keys into the field. Hit save and you have your Plexity account registered to NAD. And there you go. This says connection tested successfully and your Plexity account is connected to your NADN. And you only need to set up the credentials one time.

Afterwards, you can simply pick from the account credentials that you've set up after you've connected your account or your API keys in this case. What you can do is to choose the operation that you want perplexity to carry out. In this case, it's a messenger model. And the model that we want to work with is the Sona Pro in this case. And there are other models that you can choose from such as the Sona Deep Research or Sona Reasoning Pro. And each of these are

dependent on the use case that you want to achieve. The deep research is going to give you a large size of output rich with data information and is perfect if you're looking to do a very detailed research about a topic. But in this case, because we're only looking for the headlines of the AI development news, we want to choose Zona Probe. And as with the other AI agent nodes, the typical components that you have is the user prompt as well as the system prompt. And

you can do that by adding a message and changing the user to a system. And there is a slight difference between the workings of a perplexity node and those of the other AI agent nodes. And specifically, one of those is that perplexity will require the system message to come first before the user message. So, what you want to do is to swap this around and choose the system prompt as the first prompt and the user prompt as a second. Now, within the system prompt, here's a prompt that I've

come up with. So, it says, "You are an expert AI research analyst specialized in tracking and summarizing the latest developments in artificial intelligence. Your task is to deliver concise and up-to-date news summaries, focus on new AI model releases, research breakthroughs, and strategic moves by key AI players. So that's the system promp. As for the user prom, what I want to do here is to prompt it effectively so that it summarizes and extracts the most relevant information or news for

me. And I'm going to blow this up so that's easier for you guys to read. And here I go. It says find and summarize the most recent AI news within the last 24 hours. For reference, today is, as you can see, this is intentionally left blank because I want to drag the variables of today. And in order to find that, you would go to variables and context. And this is applicable for every single workflow. You're going to have a default variable of the current time as well as the current date. And in

this case, I want to drag the value or the variables of the current date and put it here. And this will dynamically change the value depending on what the date is. And so you can see on the right hand side it says today is date time today's date. And the reason why I want to do that is because a lot of the times the AI is prone to hallucinate the timing of the day. So when you tell it to get the most recent news, it doesn't have context on what today is. So when

you tell it to get the most recent news in the past 24 hours, often times it might hallucinate the day to be a day within last year or the year before. So this way we ensure that the AI has context of what today is and be able to focus on news that are coming in from the past 24 hours. And also I've added in to make sure that it prioritizes research breakthroughs and key announcements by organizations like OpenAI Anthropic Google Meta Mistral, XAI and Hunking Face. And this

is just some guardrails to make sure that it focuses on the news that are most interesting to me which is the development and the release of new models of AI. Okay. So now that the system and user message has been set, the last thing I want to do is to go to add option and click on the dropown button and perplexity has a very neat feature which is the recency filter. So we can set the search recency filter to just within the day. So in this case it's going to restrict the search to

within the most recent news that have been put out there. Okay, now we're ready to execute the step. And as you can see, the output is various types of data that has to do with the research output as well as some of the relevant information regarding the search. I'm not going to go through each of these variables. But what is interesting to us would be the number of citations here, which means are the number of news outlets and links that it has found to be relevant to your search and also the

search results. And finally, the output content which is in natural language where perplexity will respond to you and say there have been several notable AI developments and announcement for the last 24 hours particularly concerning major strategic moves and those reinvestments. And what we want to do here is to pin the data so that we don't have to rerun that every single run is going to use up the perplexity API token. We want to make sure that we're being cost

effective and prudent about it. The same thing with the schedule trigger. I'm going to pin this data so that every time we run through the workflow, it's not going to exhaust a new API token and provide new data. After the flexity node, what I want to introduce is the formatter agent or in this case the checking agent. We're going to use OpenAI in this case and we're going to pick a simple message and model action as part of the workflow. And as you can see, the output of the perplexity node,

which was the previous node, becomes the input of the OpenAI node. And again, I already have my account all set up as we've covered in the previous sections. So, you should have the same account set up here as well. And we're going to leave the resources as text operation as message and model. And we're going to pick a model here. In this case, we're going to pick a GPT 4. That should be enough to check against the log. And just a reminder of what we're doing here with this node is

we want this node to check against a specific Google sheet log of past headlines that has been recorded. And the reason we do that is because some headlines are going to be reported twice, three times, four times, or repeatedly depending on how big the headlines is. If we don't add this particular note within the workflow, what happens is it's going to report some of the headlines again and again thinking that it's a new headlines in the past 24 hours. We're going to rename this news

checking agent. Now for the user prompt, what I'm going to do is I'm going to give it a set of prompt here and I'm going to blow it up so that you can see it says here's today's AI news list from Perplexity. So I'm going to add the summarized content from the previous perplexity node which is under choices under message and the variable is called content and we're going to just drag and drop as you can see in the right hand side this is the whole chunk of the

summarized news headlines that came from perplexity and then later on I'm going to ask please cross check the news against the past news lock sheet and remove duplicates So this is the name of the news lock sheet that I'm going to create later on so that they can compare and check against such that there won't be any duplicate news on the output. I've also added here that we should ensure each item has a clear impactful one to two senses summary. So there's a bit of

summarization task here. Also after each summary include the full unfold source URL. This is to make sure that you're interested in that particular news. You can click on that URL and get access to where it's been cited from. Use bold to highlight company names or major updates. This is just for readability and add spacing between news items for readability as well. And at the end, I've added tip perplexities output news are all duplicates from the past news

lock sheet. Respond appropriately with no notable AI development news in the past 24 hours. is just to make sure that it's only generating content when there are new headlines and not recycling headlines again and again. So that is the user prom. Meanwhile, we need to add a system prompt. In this case, we choose an add message and we're going to choose a system message or a system prompt. And in the system prompt, we're going to do a simple prompt. And I'm going to blow

it up to say you are an AI news format and your role is to process, check and clean AI news result fetch from perplexity to ensure readability and that past headlines are not repeated. I'm going to add when checked against Google sheet tool named past and use lock. So this is just to ensure that it knows that the tool exists and that you're supposed to use that to counteract the news headlines and make sure they're not repeated. Okay, cool. So now we are going to add a tool here

which is essentially the Google sheet tool. All right, click that. And I've already have my Google Sheets account connected, but we've covered how to connect your Google Sheets or Google Docs or your entire Google account through a Google Cloud console in the previous section. So, you should have the same setup. Under the tool description, we're going to set automatically because we're going to let the AI decide when to use this tool. At the same time, we're going to have to

determine some of the configuration here. And under resource, we're going to want to to refer to a sheet within the document. And the operation is to get rows because we're not trying to create new sheets. We're not trying to update the sheets. We're simply trying to check against the sheets if the headlines are repeated. So, we're going to use get rows. Now, we need to fetch a document. But just before we do that, we need to create the actual sheet where all the

information of the past headlines are going to be logged. So I've created a sheet here called the passi news log and it's a simple sheet with a date column and a headlines column. So the date is going to correspond to the date of the headlines. And the headlines basically is going to say the content of the headlines in one or two sentences. Now let's go back to the workflow. Once you have the sheet set up, you can then find the sheet just by selecting from list

and clicking on the right one which is pass AI news lock. And then later on you can choose from the sheet the correct sheet in this case which is sheet one. I only have one sheet in the document. So that's the correct one. You should be able to see now and that's it. And just before we go, we want to rename this to pass AI new law because we want to make sure that the AI knows that this is the particular Google sheet that we're referring to when we told it that there's an attached tool to

it. Now, going back to the workflow, we're going to run this particular node here based on the configuration that we filled it. You can see based on the data that came from perplexity is checking it against the news log which in this case is an empty sheet. So there's no headlines to be checked against but still doing that. And finally the output is here's the formatted AI news which is Julius AI has successfully raised 10 million funding round amongst other things. In this

case, the next node that we want to introduce is the email node because right now all the output lives within the workflow. Just like in the previous section, we're going to attach a Gmail node. But in this case, we're going to still choose the send a message action. But the difference, as you can see, is that we're not attaching the Gmail as a tool for the checking agent to leverage on. Now, why is that? And what's the difference between attaching Gmail as as

a tool versus Gmail as a subsequent node to the AI agent node? And the difference is that when we attach the Gmail tool to an AI agent note, the AI agent has the liberty to choose whether or not to leverage the tool or use the tool. In scenarios where AI agent hallucinates, they might actually use the tool when they don't need to. They might not use the tool when they actually need to. Having Gmail note as a note that is chained up to the workflow like this ensures that any then runs through the

note regardless of what the AI agent thinks. In this case, we make sure that the note is run no matter what. And this is extremely useful when we're sure that each time of the day we want to receive an AI news output into our Gmail because a note has to be run every time a workflow is run. It is just best practice to chain it up as part of the workflow instead of connecting it to the AI agent as part of the tools that it may or may not use. Now, let's go back

to the Gmail node. And you can see that in terms of configuration, there's some slight differences between a Gmail node that is chained up to the workflow versus a Gmail tool that is attached to the AI agent. You now don't have the option to let the AI choose to define the recipient, the subject, and the message. you actually have to hardcode it into the node. And I use the word hardcode, but actually you're simply dragging the variable and dropping it into the field. The fields appear to be

the same as when you have a Gmail node attached to your AI agent. So, we're going to leave it as that. But here's where it gets a little different. So the recipient that you want the output of the Gmail to be sent to should be consistent because you want this to be a daily operation sent to the same set of email addresses. So in this case I'm going to put my email and under the subject I'm going to put daily AI news digest. And this doesn't need to change because

I know what it is. And email type because it's all going to be text. I'm going to choose text and the message is actually from the content here. And as you can see the content itself, it says here is formatted AI news. So this is not ideal in the way that I want to receive the summary. So we can actually prompt this a little bit better. So once we're done with this, let's go back to the news checking agent and under the user prompt and we blow it up. Let's add

an output format rule output in text only and start the news daily news summary with here is today's AI development news today is and I'm going to just track the today variable and drop it here. So, I wanted to start this way so that it makes sense. Every time I open up the email, it's going to say, "Here's today's AI development news. Today is that particular day." So, I know that I'm getting the latest news from the headlines. Okay, now that's done. As you

can see, when I make any changes, it's going to turn the node yellow. So, we're going to run it one time and let's see what the output now is. Here's today AI development news. Today is 7th, sorry, today is 29th of July, 2025. And then the news. So, okay, that's the format that I want it to be. I'm going to open that up again and pin it so that I don't have to rerun it every time. And within the Gmail, this is the content that I want to drag into the message field. So,

that's good. And remember in the previous sections, we know that it's going to automatically come with an added attribution within the email. So what we want to do is just click add option and it toggle off the append attribution and then we're going to try to execute step. As you can see there has been some actions and then email has been sent. So let's go to our email inbox and see what we've received. So this is the email that I've received and it says here's today's AI development

news. Today is this date. Of course this formatting is not ideal. You can go into the prom engineering again and try to format it in a more readable way, but essentially in terms of formatting, it's much easier to read now. And of course, these are the news, the headlines, and if you push it to production, you're going to be receiving these emails day in day out and keeping yourself updated with the latest AI development news. Going back to the workflow because we're

not quite done yet. Even though we're now receiving the daily news update and I'm going to pin this as well is that remember the AI news log that we've introduced here. We want to make sure that whatever news that have been researched in the past 24 hours has been logged into the sheet. That way the very next day the agent or the news checking agent can then check the log and make sure that the headlines are not repeated again. and the agent will always be checking against past news to make sure

that it's not repeated. So in this case, what we want to do is we want to introduce a Google sheet node. Click on Google sheet. As you can see, there are a couple actions that we can do with Google sheet. And what we want to do here is to choose an append row in sheet. And the reason why we choose append row in sheet is because we want to add new information on an existing sheet. So we've got the Google Sheets account connected already as usual as what we've covered in the past section

and under resource we want to access the sheet within the document and the operation we want to do is to append rows or append new information. Now under document what we want to choose is the past AI news. So just type in the title and you can choose that. The alternative is actually you can link it by typing in or copy and pasting in the URL or the ID of the document. And once you've typed that in, you can then choose the list of sheet. And again, we have only one sheet. So the sheet sheet

one and once you've done that, you'll be able to see the columns that now exist within that particular sheet. And within the sheet that we've created right now, it's completely blank because there are no headlines. They've been logged in. We have two columns, which is date and headlines. And if you go back to the workflow, there's the date column and there's a headlines column. So now what we do is we want to populate this particular rows in under these particular columns with a

specific data. So in this case, we want to choose under variables and context the today variable and drag that and drop it under date. So that way it's going to always populate the date column with the value of today's date. And under headlines, what we want to do is we want to choose under the news checking agent the output of the content. And now as you can see when you drag variables from other nodes, you don't necessarily always have to drag it from the previous or the immediate

previous nodes. You can drag it from nodes that were from previous instances in the chain. So in this case, I'm going to drag the content variable from a news checking agent and just drop it into the headlines. Now with that done, I'm going to try the execute step to see what it does. And as you can see, it's telling you that it's added the date component or rather today's date into the date column and headlines into the headlines column. And of course, the way the logic works is

it's going to pick the topmost row that is unpopulated within the sheet. So it's always going to pick the next available rows as you go. So now that that's done, we've ensured that there is some form of loop in terms of the way the workflow checks for new headlines. And now with the workflow, we've created a form of a loop where the perplexity agent every day would go out and search for the latest information on AI development and a news checking agent checks against

past logs of the headlines to make sure that the information is not repeated before sending it into your Gmail. All of that gets stored within a Google sheet every day. And then the next day, the same operation is going to happen again. The research agent is going to go out into the internet and check the most recent and relevant news for you. And then we also have the agent checking that against the Google sheet together with the news that were locked in the

previous days before sending it out into your Gmail. So that way you can be sure that the headlines that you receive every day are really the most relevant and the most recent news that you can get. There are many other options of tools that you can use along this workflow. Perplexity is just one of the options even though in my opinion it's one of the most advanced out there when it comes to search. OpenAI can be replaced with any other LLMs as well. And you can replace a Gmail with a

Telegram node or Slack node or any other platforms that you spend your most time on. In any case, I hope this section provides a good understanding of how a general logging mechanism of the workflow can possibly work. So that's the end of the section and I'll see you in the labs. In this section, we're going to have a little bit of fun. So since we now know how to create an AI agent on end and how to connected to our Slack accounts, we're going to try to see if we can have the AI agent fully

take over our profile and respond on our behalf, aka do our job for us. So in this case, this is the same workflow that we've built in the past section. The first thing we need to do to have the AI agent respond on our behalf is to go to our Slack API and reconfigure some of the OOTH permissions. And what we want to do here is simply go down to the scope section. And in the past section, we filled up all the bot token scopes as required. But in this case, we're going to scroll down to the

user token scopes and fill it up with the required scopes. And these are the list of required scopes that are typically recommended in order for it to function well. So as you can see we have channels history to read the channels just in case we want to respond and interact uh within the channel and we obviously we have the channels read chat right groups history as well as some read and history permissions and this all depends if you want the bot to respond on your behalf in a channel in a

direct message or in a group message. So once you're done adding all the new O scope under the the user token scopes, what you need to do would be to reinstall the app. There will be a notification popup that comes up here. I'm just going to show you right here. So if I were to add

let's say an admin apps read. What will happen is it's going to ask me to restore my app over here. So just go ahead and do that and you're good to go. And just before we go under the bot token scopes, you do need to add one more permission which is essential which is the chat write.customize. And this just allows the bot to send messages on your behalf. All right. So once you're done, you want to copy the user o token and go back to your n workflow. And here you're going to create a new

credential which I've done here. But essentially what you need to do just do the same thing. pick access token and paste the user O token here. I'm not going to click on save because I've already created one, but it's the same exact process as we've done in the previous section. And once you're done with that, you want to toggle over to the event subscriptions. And what you want to do is just unfollow the subscribe to events on behalf of users. In this case, also add these four event

subscriptions, which is message channels message.groups message and message.mppim. This just covers most of the use cases that you might need. And if you want to know a little bit more about the permissions and how it all works, I encourage you to go into the Slack documentation and to check it out yourself. But now I'm going to go back to our end workflow and reconfigure some of these nodes. So in the first trigger node, previously we have the bot/ app mention.

Now I want to add on just any event as one of the event triggers. The reason for that is I want to make sure that I'm capturing direct messages when my team members are chatting with me. And I also toggled on the watch o workspace. The reason for that is again I don't want to be just watching a single channel or a single chat. So when I toggle this on any message received will constitute a trigger event which would then run the workflow. And scrolling down under

options what I want to do is also add the username or ids to ignore. In this case, I'm going to fetch my own ID to ignore my own messages because right now how it works is it's going to trigger on any event, which means it will also include any messages that have sent to any channels as a trigger event. So, how do I get the user ID? Well, you can get your user ID from your Slack channel by just simply clicking on profile and clicking on the three dots here. And

you're going to be able to copy the member ID. So that's the ID and you can go back to your NDN workflow to the trigger node and essentially paste the ID under the expression for the username or ID string ignore. Cool. For this demo, I've created a fictitious workspace. I've added one of my colleague Michael Forester into the channel. And obviously this is not the real Michael. This is just a profile that I've created. And again, as you can see, this is just a demo workspace. And

I'm even on a free account on the left hand side. You can see that it's 23 days left on the trial. And what I've done was I created another account as a fake Michael Forester. And it says Michael F, which is me. It says Michael F, which is this account. And the left hand side, you see this is my account. And the reason why I'm setting up these two accounts is so that I can show you how it all works when my team member chats with me on a direct message. So now I'm going to try

to complete the reconfiguration of the entire uh workflow. And what I'm going to do here is go into the agent node and everything stays the same with the exception that I've added a system message here. So essentially what I'm telling the agent is that you are maronei a team member at corkcloud and your job is to impose a maronei as well as you can and respond to his team members message on the behalf sound friendly and natural in a typical tech working environment. So as you can see

is a pretty broad system message. Um, you can obviously prompt this much much better, but I'm going to just start with that. But one more thing that I'm going to do is I'm going to go to a chat model and I'm going to just toggle this to GPT5 because it just came out.

And GP5 in my experience has been great at responding to complex queries um and using tools when required. So I'm going to leave it as that. The simple memory is still attached. And on the last note, which is a send message note, I made two changes here. And the first one is, as you can see, the channel ID, I made it into dynamic ID. It's showing an error here right now because it doesn't have any data populated just yet. But essentially, I want to make sure that this is going to

be dynamic because the workflow now is triggered by any events watching the entire workspace. So, it's not necessarily going to be restricted to one single channel. So it could be a direct message, it can be a group message as well as a channel message. So I just want to be able to dynamically reply to that specific channel where I'm interacting with people on. And the second thing that I'm going to change is under option, I'm going to say send as user. I'm going to put in my

username here which is Mark. And that's it.

Okay. So I'm going to hit execute workflow here. As you can see, it's waiting for a trigger event. So, I'm just going to go back to our Slack app.

In this case, I'm going to use the Michael Porser account here to chat with me. So, I'm going to say, "Hey, Marone." All right. So, let's go back to the workflow. As you can see, it's getting a trigger. It's hidden the AI agent and it's responding to my message. So, let's see what kind of message or response that I'm receiving back. It says, "Hey, what's up? Need an update on anything AWS/resour or is there something that can help unblock?" All right, sounds pretty

helpful. And I think it threw this in because I said, you know, pretend to be somebody in CodeCloud. So, CodeCloud's associated with cloud technologies, etc. So, it's probably just throwing that in. Okay. So, I'm going to go back to the workflow. I'm going to hit execute workflow again. So that it's now waiting for my trigger. And using Michael's profile, I'm going to type. How was your weekend? And I'm just going to stay social. Not going to talk about anything about work. So there you go.

And it's responding pretty good. Kept it low-key. Got some rest. Did a bit of planning over the week. I also sketched out a couple of tweaks for the AWS and the zero pipeline that I'll share after the stand up. Cool. All right. Um, it's adding it own flare. So, not sure about that. Uh, probably need to work on the prompt a little bit, but cool. Um, so, so it's working quite well now. Responding as myself, even though I don't normally sound like that. Um, I don't necessarily work intimately with

all the cloud stuff, but I'm just going to go back to the workflow here. And I want to try to make the agent a bit more useful and give it more context uh than it currently is. And this is where I'm going to try to introduce a pretty simple rack system. And in this case, I'm just going to add a tool and this is just going to be a Google doc tool because the reason why I'm doing that is I realized that people are going to start asking me about projects etc. So what I did was I created a document

which is a Google doc document and essentially this is completely fictitious but it outlines kind of the update of the project progress in terms of some of the stuff that we're trying to do and this is again completely fake but it's just a document so that we can see how it all works. All right cool I have this Google doc drafted out. This is where I put all the fictitious updates. So I'm going to connect that here and under the Google doc node what I want to do is is a get operation

and I'm going to go back and just copy link which is a URL link of the cloud project status and I'm going to paste that URL here. All right. So I'm not going to do anything with this node. This is just an attach tool. I'm going to go back to the AI agent and under system prompt I'm just going to add a tool description. Use the Google doc tool when asked about project updates. Cool. All right. So, I'm going to just make that change. I'm going to save that and I'm just going to click on execute

step here and go back. Ask Michael.

I'm gonna ask how is the is your project going. As you can see, it is kicking it to the air agent. It is thinking it is going into the document checking the latest update of the project before kicking it back into Slack. So, let's see what it responds to me. So, there it goes. says quick as your project I made objective interactive lab design done 65% complete ETA 15th October 2025 now let's see if that's correct

so this says that the lab is 65% complete and expected completion 15th October 205 so it's successfully fetching the relevant information into the message however as you can

So, it's giving me the right information, but as you can see, it's missing a little bit of a human touch. So, that's probably something I can work into the assistant prompt for it to respond more like me and more humanlike. But at rarely, this gives you a good understanding on how you could leverage AI agent. Maybe not to impersonate yourself just yet, but in a lot of other use cases. As you can see, once you've created a rag agent like this, this could function as your technical support

or just a bot FAQ. And this could work for HR, legal, marketing, whatever the case may be, or even customer support. But there you go. This section is to really just familiarize yourself with the select permission logic and how you can potentially leverage that to its full extent. Again, this is just for fun, and we're not recommending you to replace your day job with an actual AI agent just yet. See you in the next one. In this section, we're going to walk you through

how to set up the Slack API and connect it to your NAN. And then we're also going to go through the various different permission levels as well as the logic in terms of integrating Slack into your NAND workflow. If you're already familiar with how Slack API works, feel free to skip this section and go to the next one. So, first where you want to head to is the Slack API page, which is api.slack.com. And once you've signed in, you want to go to your app section and hit create

new app. And what you're going to do is come up with an app name. In this case, I'm going to call it the end devilbot. And pick your workspace and hit create app. Now, what you want to do in your bot configuration page is first head over to permission. So, there are a couple things to keep in mind here in terms of the architecture of the bot. So, first we need to configure the permission level that we want to grant the bot on Slack. In this case, we want to scroll down to the permission scope

and we're going to hit add an O scope. In this case, a couple of basic permissions that I want to start off with. So the first being the obvious which is the app mentions read. So this is going to let the bot read any messages that you've sent to the bot directly by pinging it. And the second one that we want to add will be the chat write which allows it to send messages as any demo bar. And just to make sure that it could read our messages on channel we want to add channels read and

group read as well. Lastly we want to make sure that they could actually see the name of the people that are sending the messages. So we're going to add the user profile read as well as users read. So that should be enough for now. And so we're going to go ahead and install the bot to our Slack workspace, which is called the Slack automation lab. And we're going to click allow. And again, you need to be an administrator of your Slack account to be able to do this. As

you can see now, we've got a bot user O token generated. So we're going to hit copy on this because we're going to use this to create a Slack credential back in our NN workflow. So going back to our N& sheet, the first trigger node that we want to introduce here is the select trigger node. And I want to make sure that we pick from the selection of the trigger nodes and not the action node. In this case, we're going to hit the onbot app mention. And I already have a

Slack vential preset up here, but I'm just going to recreate another one just so that I can show you how it's done. So, we're going to name this Slack and then demo code cloud. And I'm going to paste the key here and hit on save. As you can see, the green bar shows up. Connection tested successfully. So, I'm going to go back to the API page here. And right now I'm going to go to the event subscription because I want to make sure that's listening to the events

that I've specified. I'm going to toggle this to on. And for the request URL is a URL that I'm going to grab from my endn workflow. So I'm going to hit the web hook URLs here. As you can see, there are two URLs provided. The first one is the test URL and then we've got the production URL. The production URL is the URL that you're going to use when you toggle into production. But right now, because we're doing it on staging, we're just going to take the test URL,

copy it to our clipboard, and go back to the API page and paste the URL. And as you can see, when you do that, it's going to say that your URL didn't respond with the value of the challenge parameter. This is because you need to go back to your Slack trigger and execute step and your workflow will be ready to receive the trigger. That's when they will send back the challenge parameter to the Slack API. Now, in this case, before we can hit execute step, we need to populate the field, which is the

channel to watch. And there are a couple ways to pick your channels. As you can see, you can either get it from this, by ID, or by URL. So, we're going to pick from this. Click on all Slack automation lab. So, this is a general channel that anybody can join. So, I'm going to hit execute step. I'm going to go back to the API page and hit retry. And this time, it's going to say verify. And just before we go, I want to make sure that subscribe to the right event. So, under

subscribe to bot event, I want to add bot users event. In this case, I want to add at mentioned, which is just making sure that it's listening every time that this been mentioned. So, I'm going to hit save changes, and we should be ready to go. All right. And then, going back to our Slack page, as you can see, it's listening for an event. And we don't have an event right now because nothing's been typed into our Slack channel. And here, for it to listen to

the channel, we need to add the app into the channel. And the way to do that is to go up to the member section here. Click on that. And where you want to go is toggle over to the integration bid and select the app that you want to add. So there you go. The N demo bot is now added to the channel. Now we're going to just do a trial run by hitting execute step. And that's going to wait for any triggers while listening to the channel. And going back to the channel, what I'm

going to do is I'm going to ping-demo and I'm just going to simply say hello. So I'm going to go back to my NN. As you can see, it's now populated the SL like trigger node. Now for SLE, there's quite extensive amount of output payload and the information that gets passed on to the triggers. So of course the most important bit is the text itself or the content of the text which is hello. But as you can see, you're also being passed other types of data like the user

ID as well as the channel ID and the event timestamp. So all of those are going to be useful depending on the use case of your workflow. Now once you've set it up, next note just to play around with this is we're going to add an AI agent node

and we're going to pick define below and we're going to drag from Slack the text content

and we're going to add a chat model.

In this case, I'm just going to pick follow mini. I'm also going to add some memory because I want to make sure that it's going to be able to recall contextual knowledge or information from previous compositions. So, in this case, the session ID that I want to pass to it is a channel ID.

I'm not going to attach any tool for now because essentially what I want to happen is just for the AI agent to be able to chat with me on Slack. So I'm going to add the third node which is the Slack node and this time I'm going to allow it to send message back. So pick the right select credential in this case the select and demo codecloud resources message operation as send. And we're going to choose send message to channel and again we have to provide the

channel ID. Of course, you can pick from the list, but in this case, I'm going to pick from the ID. And how do we get this ID? In this case, we want to go back to the select channel. As you can see, if I click on the title of the channel or the name of the channel and I scroll down here, you're going to see channel ID C099 AJ1 KP46. So, I'm going to copy that and go back to my edit end workflow and paste that in. So I'm just trying to show you that there are two ways to do this which is one by

the list and the second one by the ID. Actually there is a third one which is by URL but typically selecting by ID will work for all cases.

Okay. So I don't have the parameters yet to drag into the message text. So I'm going to execute previous nodes. And there you go. There's an output which is hello. How can I assist you today? I'm going to drag that, put it into the message text, and I'm just going to hit execute step. All right, let's go back to our Slack channel. And as you can see, it's replying to me on the channel saying, "Hello, how can I assist you today?" And it also says automated with this

workflow. So, we just want to click on add option. We want to click on include link to workflow and toggle that off. So, I hit execute step again. And when you go back to a slack channel, it says, "Hello, how can I assist you today without the automated open end workflow appended to it?" Cool. So that's a simple way to connect your Nen workflow to Slack. And of course, there's a lot more cool stuff that you can do on Slack, such as configuring the Slack model and also

being able to reply as a user. I'll see you in the next section. So one of the most useful features of ENN is the ability to tap into thirdparty tools to be used on your workflows. And these could include tools that are not natively available on NDN. And the ways you would do this would be through API calls, MCPS or webO calls. So in this section, we're going to run through the foundational workings of a typical HTTP request nodes as well as how to make API calls in three different scenarios. So

the first scenario, we'll do a simple API call to a public API endpoint that doesn't need any authentication in order to get some fun little facts about cats. And on the second scenario, we're going to make an API call to the open weathermap.org to get you the latest information about the weather on a specific city that you requested. And finally, we'll make an API call to a web scraper called Firecrawl that could intelligently scrape any web pages that you like. So,

we're going to go ahead and build the workflow here. And the first trigger note that we want to choose in this case is a trigger manually note. The reason why we're choosing this is because it's a simplest one. And in this case, because there's no input that we want to transfer into the HTTP node at this point, we're going to start with this. So, we're going to hit execute flow to see what sort of data that populates it. So, we're going to open it up. And as you can see, it's an empty payload in

the output data. And this is good enough because the next node is just the HTTP request node which does not need any input. So in this case I'm going to hit the HTTP request node. There are a couple options that you can choose from in terms of what type of HTTP request that you're trying to make. The most popular ones obviously the get and the post. In this case we're going to stay with get. And the public API URL endpoint that we want to hit is this catfact ninja/fact.

So there's no authentication required and we're just going to hit execute step. And as you can see, it returns a data output of a random fact about cats. So the random fact that we fetch is two members of a cat family are distinct from all others. The clouded leopard and the cheetah. The clouded leopard does not roar like other big cats, nor does it groom or rest like small cats. Okay, so that's very interesting. So now we like to do something a little bit more

useful by calling an API on the weather app. So in this case, we're going to delete the HTTP node and reintroduce a HTTP request node again. In this case, we're going to choose post. And the public endpoint that we want to hit in this case can be found at openweathermap.org/curren. And you scroll down to the built-in API request by city name. You'll be able to copy and paste the API endpoints straight into your workflow. So going back to the workflow, we're going to

paste this. And before I do anything else, I'm going to blow this up. And as you can see, there are two variables here. The first one being the city name and the second one being the API key. So for the city name, we want to pick a city that we're interested in. In this case, London. And for the API key, we need to key in a valid API key, which can be obtained from the website. So going back to open weathermap.org, the first thing you need to do is to sign up and ask for free. And once

you've signed up and gone through a little fun onboarding questionnaire, you can head to my API keys and you'll be able to view all the API keys that you have with Open Weather. And you could also generate a new API key by clicking on this button over here. But in this case, we already have one set up. So we're just going to copy that and paste it back in the workflow. Cool. Now that we filled that in, we're going to execute step and we're going to toggle this into the schema format. As you can

see, the temperature, the maximum, the minimum temperature, as well as a cloud coverage situation. Now, as you might have noticed, I've actually input the API key in the API endpoint itself. But a better practice within Noden is to set up an authentication that's going to persist even after you're done with a note, which means you can use the same credentials or API keys in a separate note if you happen to need to work with this particular app. So, I'm going to

show you how that's done. In this case, I'm going to hit authentication, select generic credential type, and choose header O. And why did I choose Brit? And the reason why I'm choosing header because the API keys itself is contained within the header section. Now, we want to set the new credential. So, we're going to name this credential open weather map demo. Okay. And under name, I'm going to do X-API-K. And under value, I'm going to paste the same API key. I'm going to hit on save.

And there you go. My credential is saved under the name open weather map demo. Now after setting it up as a header O, what I can do now is actually remove the API key section from the API endpoint. Now let's run that. As you can see, it's giving me back the same information. The only difference is now my API keys lies within the preset header authentication section here. And if I were to create another node that works with openweathermap.org, or I can simply use

the same header off credentials wherever I go. So this is just a very easy way to go through your workflow. Great. So now we're done with the weather app. What we want to do is to try a different scenario where we're actually calling an API endpoint of a web scrape. So let's delete this node. And what we want to do is again to reintroduce the HTTP request node. And this time we're going to make a post request to a web scraper endpoint called firecraw. So we're going to

rename this firecrawl scrape. So when you head to fcraw.dev, this may look different depending on whether you've signed up or not. I'm already signed in, so this page will look slightly different for you, but essentially to sign up, you just have to go through a fun little onboarding questionnaire and pretty much it's straightforward for you to sign in. And once you're in, you want to head over to the dashboard and even on a free plan, you'll be given an API

key to start scraping with. So where I want to go from here is to go to the docs because this is where all the API documentation is going to rest at and go to the API reference. In this case, I want to scrape. So this is the post request for scrape. I'm going to hit on try it and copy the curl command up here. And before copying the curl command up here, what I'll do is I'm going to put in the URL of the page that I want to scrape. So in this case, the page that I want to scrape is actually

TechCrunch, specifically the Gen AI section of the news. So, I'm going to copy that and go back and just paste the URL here. As you can see, this going to change the JSON body of the URL to the URL that I've intended here. Of course, you can do this manually within the workflow itself as you import the curl command, but I thought it easier to just do it beforehand. And we can just copy the whole curl chunk and go back to the workflow here and click on import and

paste the entire curl command. As you can see, there's a post method to this particular URL. every one of these fields are configured the way we needed to. And under authentication, we're going to set this up again the same way we've set it up for the open weathermap.org. So, we're going to hit generic credential type and then we're going to pick header o because that's where the authentication credentials lies for this particular API call. And then we're going to create a new

credential. So, we're going to call this credential fire crawl codecloud demo. And just before I go any further here, I want to go back to the documentation and look at the the header within the curl command. In this case, what we're going to pay attention to is the name of the authentication here, which is authorization. And we're going to type in authoriz. And under value, we see that it's got bearer space API token. So, what we want to do is go back. I'm going to toggle this to expression so

you can see what I'm typing in is bearer the API token which you're going to get by going to the dashboard and copying the API key here and pasting that into the field. So there you go. Hit save and that credential is going to be saved. Okay. So going back you notice that under the send headers portion is toggle to live and it actually has the same thing which is authorization which we don't need anymore because we already have it all set up here. So we're just

going to toggle that off and then focus on the body right here. So, we've already set the body up earlier before copying it over. So, there's nothing much we need to do here. So, we're just going to hit execute step. There you go. So, there a couple of output data here. As you can see, the main content is really under the markdown. And I'm going to toggle this to a table format so it's easier to see, but it basically feeds you the headlines of the news of the day

that has to do with Gen AI. So, as you can see, Tech Crunch covers the latest news, da da da, headlines only, learn more, and here are the links to those headlines. And yeah, so this is a simple scrape. So it's going to scrape all the information within that particular web page. But of course, you can format this more within firecrawl itself. But in this section, I just want to show how easy it is to set up an API call to call a web scraper or any other type of apps

that might be interest or might be useful to your workflow. So, building on to that, I wanted to show what happens when you have a post request that requires a get for you to obtain the result of your post request in the first place. So, we're going to stick with firecrawl. In this case, under fire crawl, there are a couple of features that we can use. So, one of them is extract. So, how's extract different from scape? Well, extract is an AI powered way for Firefly to extract

structured data from either single page, multiple page, or even an entire website and any of the subdomains or subpages associated to those websites. So, it's an extremely useful tool for us to use. So, what we want to do here is head over back to the docs. Where you want to go is go to the documentation tab and scroll down to extract. There's a pretty good curl example that we can make use of here. So I'm going to copy the entire curl command here and just go back to

the workflow and hit import curl. You can see all the fields here that needs to be configured are all added. And what I want to do first here is to select the same authentication that I've set up previously under generic credential type and header o and firecrawl codecloud demo. So as you can see since we have already set up the header off here we can toggle this off and move on to the JSON body. Now the reason why I picked the example is because this already been

pre-filled. So it's easy for us to run this example so that you don't have to really fill in every single sections or variables that is required to be filled. What's happening is that the prompt that's given to extract the company mission whether it supports SSO whether it is open source or whether it is in Y combinator from the page. So that's the prompt for extract. So it's going to try to get relevant information surrounding that prompt. So let's go back. We're

going to stick with that and we're going to hit execute step. So when we do that, as you can see that the note says it is executed successfully. What it means is it's pushed through the post request to the API endpoint successfully and it's currently processing the post request. Now because it's extracting for a couple different pages and specific information, it's going to take some time. So what we want to do now is wait, right? So and how do we wait within the workflow? Well, you can actually

introduce what we call the wait node. So introducing the weight node, you can actually configure the amount of time that you want to wait. So in this case we're going to hit 30 seconds and of course the weight unit is in seconds and you can change that to minutes, hours and days depending on your needs but we're going to wait 30 seconds here. Going to remain rename this to that. Okay. So I'm going to hit execute step as well. So the data is populated here. But what I want to do with the fire

crawl extract post is that I want to pin the data because every time I run this particular node, it's going to exhaust my API token. It's going to consume my API token and I want to make sure that the pre-populated data stays here for every execution run. So that's going to be super helpful for me. As we wait for the wait note to complete the load, what we want to do here is to introduce the HTTP get request. So going back into the firewall documentation, what you want to

do is scroll down for that example and here's the curl get command that you can copy and go back to your workflow. Hit import curl. And basically all the required field has been set up. So if you look at the documentation, you'll see that the extract ID comes from the slash after the endpoint. So what we want to do is introduce the same here. Use a slash and toggle that to expression and drag the request ID, the post request ID into the field here. And of course, this is the same post request

ID as what the previous nodes was passing the same data into the weight node. and hence we're using that in the field here. So essentially what we're telling it to do is to get the result of this particular post request ID and return those results here. So I'm going to rename this firecrawl get request. All right, things are pretty much set up here but we have to again select the same authentication method in this case the firecrawl codecloud demo and then we're going to hit execute step. So

there you go. As you can see, move this into a schema format and it's extracting the information that we want, which is a company mission. At the same time, it also tells us the status which is completed. And this is important because as you wait, I know we put in 30 seconds here. It's not necessarily going to be completed within 30 seconds. So, let's say after the post request, we wait 30 seconds and then the get request launches and the status is not yet completed. What will happen then? Well,

the workflow will break down. there will be an error and the workflow will stop working. So to avoid that scenario, what we want to do is to create what we call a loop and in this case we're going to add an if node so that we can continue that logic. And what we'll do here is under firecrawl get request we want to take the status and drag it into this field here. And because this is going to be strings as you can see completed is a string. If the string is equal to

completed, as you can see, I test run that and basically this is true. It falls into the true branch. It's populated. False branch is not populated. It's true because the JSON status here is completed as per the requirement. So if that's true, it's going to continue and maybe send that completed extracted data onto something else such as maybe sending it to let's say a Gmail send a message note and we can populate the content which is in this case a company mission let's say

and the message and I'll just say here company mission right so two let's say I'm just going to pick maronecloud.com so it doesn't matter because this is just an email or any other output node that you want to set However, if the status is false, what it means is that after waiting for 30 seconds, when we try to get the result of the post request, it's still not ready. So, what happens is under the false branch, we're going to wait another 30 seconds because

we want to wait until it is ready. Okay? And we're going to wait another 30 seconds and we're going to loop this back onto the firecrawl get request. As you can see, the yellow highlights coming out because there are some changes that we made to the node which is connecting it with another potential previous node. This loop will avoid the breakdown of the workflow in the case where after waiting for 30 seconds the request is not ready and it's checking that by the if note because if the

request is not ready the status is going to say in progress and therefore it's not completed and it's false it'll wait for another 30 seconds and try to get the result again. And if still not ready by then it's still going to go into the false branch and it's going to wait another 30 seconds and going to try to get it again. So it's going to be in this loop until it is ready and hence the status is completed and becomes true and then it sends out as an email. So

this is how we can use loop to avoid a breakdown of workflow when it comes to an API request that requires time to process and it requires a second step of getting the result from the app. So we're just going to run this again just to make sure it's populated. But essentially that covers the principal workings of how we would go about building a workflow with HTTP request node to access API endpoints of other apps that are not necessarily native to any. In this section, we're going to

build from scratch a text to image workflow. This is how the workflow is going to look like in the end. The goal of this workflow is for you to begin with a text input specifying how you would like the image to be created in a simple format and that will be passed on to an image prompt agent that would then create an effective prompt to be passed to an image generation model in a platform called Wspeed AI. Now waist speed AI is just one of the many platforms that host video or image

generation model like V3 or Cadets. A little caveat, it is a paid platform and to be able to use the API calls, you'll need to top up a minimum of $10. Now, we'll walk you through how to set up a post API call to waist speed and how to post a get API call to get the result of the image from waist speed and then how to set up an if loop just to make sure that the workflow doesn't break down when the image or video isn't ready yet. And finally, we're going to pass on the

result or the output of the image into a simple Gmail. And the output node can be replaced by any form of outputs such as Telegram, WhatsApp or Slack. Now, starting from scratch, the first trigger that you want to hit in this case is the chat trigger node. And again, we're choosing the chat trigger node because we want to be able to tell the workflow a certain specification of the image that you want to be generated. And this doesn't have to be super detailed

because again, you will have an AI image prom agent that's going to help you craft an effective prompt. But in this case, I'm going to just populate the chat note data with a simple create an image of a cat flying through oops of rainbows. All right. And that data is now populated in the payload. As you can see, the chat input is created image of a cat flying through groups of rainbows. Cool. All right. And the second node we're going to introduce here is the OpenAI node, which is just a message

model node. In this case, I'm going to rename this image prompt generation AI. All right. So, the OpenAI account has been connected as per as how we've gone through in the previous section. And we're going to choose a model here. And we're going to pick GPT4.1. And of course, we're going to drag the chat input into here as the user input. And what I'm going to do here is I'm going to add a system message just to specify exactly what I want this node to do. And here's the system message that I've

prewritten. I'm going to toggle this to expression so I could blow it up. As you can see, I did not come up with this system prompt. What I did was I went to chatgpt and essentially asked it to act as a prom engineer and come up with an effective system prompt for a text to image generation prom engineer. So I recommend that you do that for all production cases because LLMs are just much better at coming up with system prompts than we are. and you don't really have you can do it yourself, but

I would say that starting off with an LLM and iterating it and improving the version afterwards is a much easier way to go about it. So, as you can see, it says you're an expert text image generation prom engineer working inside and in an automation. Your only task is to generate clear, vivid, and effective prompts to be passed to an image generation API. I'm not going to read the whole thing, but essentially it's just giving it details on how we want the output of the video or rather the

image prompt generation to be. Cool. All right. So, I'm going to hit execute step here and see what kind of output it gives me. So, as you can see, the content has been outputed is an image prompt generation, which is a playful cat soaring gracefully through vibrant glowing hoops made of rainbows suspended in the sky surrounded by fluffy clouds, dynamic motion, bright and whimsical lighting. magical atmosphere highlight detailed digital art fantasy illustration style. So great. So it's

describing the image the background as well as the style that we want it to be in. Cool. All right. So after the image generation prompt where we want the output to go is to HTTP request node to way speed API. So I'm going to rename this a simple way post because this is going to be the post API that we're going to call to waist speed. So going back to waist speed again if you guys are new to this platform what you need to do is sign up it's pretty easy and

straightforward there's going to be some onboarding questionnaires and stuff like that but it's pretty easy straightforward to sign up and I'm already signed in here where I will go is I will go to the explore models here and as you can see there are many models that you can try and play around with but in this case what we want to do is we're going to checkbox the text to image so that we are only given the text to image models here and we're just going to take the first one which is

Cream by my dance and we're going to toggle over to the API documentation here. As you can see there's there's a post curl command that I can easily copy and import to my workflow. So going back to the workflow I'm going to click on import curl. I'm going to paste the entire curl command here. And there you go. The fields are populated. The next thing I want to set here is the authentication method which as we've gone through. We're going to choose the generic credential type header off. And

I already have a waist speed credential set up here. But what I'm going to do, I'm going to create a new credential so that it's clear on how to set this up. So I'm going to call this waype credential demo. And under the name, just to be sure, I'm going back to the API documentation here. And under name, so the name should be authorization. And the value is bearer API key. And what I want to do is I'm going to head over to the API key section. And as you can see,

I already have an API key generated. But what you can do is you can actually create a new key and hit that create key and it'll just give you a new API key for you to copy from. But in this case, I'm going to use the existing one. Going to copy that. I'm going to go back and under value, I'm going to toggle this to expression so you can see it. I'm going to type beer space API key and I'm going to hit save. Cool. So now that's set up. Under the hitter section, I can toggle

this off because the authentication is already contained within the hitter section. So I can just remove that and focus on the body section. Now there are a couple fields here under the body section and most of it is just how you want the image to be the ratio as well as the size here. But what we want to pay attention to is really in this case the prompt because we want to make sure this prompt comes from the content output of the image prompt generation AI. And we're going to drag this here.

And there you go. The rest of the stuff I'm going to just leave as is. But of course as you were generating it you can specify it to your requirements. But in this case, I'm going to hit execute step. And there we go. We got it out. So the next note I'm going to introduce here is just a simple weight node. Now this is image generation. So which means it's going to be pretty quick. As you've seen the status here is already created. But in this game, I'm just going to wait

15 seconds for it to complete. And I'm going to hit execute step just to populate this note. And just before I go any further, I want to go back here and pin this data so that I don't have to rerun that every single run. It's going to consume my API token. So I want to be careful about that. And while that's spinning up, what I want to do is start setting up the get HTTP request, which is the same node here. But in this case, I want to go back to waist speeds API

documentation and hit the curl command for get result and go back to the workflow import curl. Import the entire thing. And again, all the fields are now configured correctly. With the get API, we want to make sure that we're pasting in the right request ID. As you can see, there's a variable here called the request ID. And we just want to first of all toggle this to expression and then remove this with our request ID from the wheat node. And we're just going to drag

that right between the slashes here. And what we're doing here basically is we're calling the post API and way speed is receiving the image request and it's processing the image. We waited 15 seconds and now we're going to get the image. But we got to tell way speed which image that we're trying to fetch and we're doing that by dragging the ID into the API endpoint. Here under authentication we're going to choose generic credential type header O and the same credential here and of course

similarly we can toggle off the headers because we already have it within our credential. Rename this to waste feed get and we're going to hit execute step. So we're seeing a couple things in the payload here but essentially the URL link of the image is the output link here. All right. So I'm just going to copy that and paste it to see what the image looks like. So this is what the image looks like. is a cat jumping through hoops of rainbows. That looks pretty cool. All right, now that that's

done, again, what happened here is that the get API was called after the status has been created. So, the result exists and is valid. But what about the case when speed is taking its time to create an image or when it's a video generation model, it's probably going to take longer than just 15 seconds. So, in the scenario where the get API call is made, when the image is not ready, it's not going to give you any result. in fact it's going to bug out or error out. In

that case, a workflow is going to stop without rerunning it because essentially it's just going to error out on this node. So what we want to do to avoid that scenario is we want to create an if loop. In this case, what we want to do, we want to drag the status string from the waist get http request and essentially say if it's equal to completed, then it is true. I'm going to hit execute step here and it goes into the true branch because the status has been completed. So the if branch acts

like a logic node where it can filter out the output based on the logic that you've set. So in this case the logic that I've set is for the status to be completed and that's true. It falls under the true branch and it can continue. In this case I'm going to set the Gmail note. Send a message. I've already set up my Gmail account. Essentially I'm going to send this to myself. The subject is image generated. And I'm going to drag the now variable just so that we can tell by the title

when this is created. And email type can be text because I just want the link in the email. Nothing fancy. And the message we're going to drag the output here so that the link to the image is sent to me via email. All right. So I'm going to hit execute step. As you can see, the email has been sent. And let's see what the email looks like. So the email looks like this. Nothing fancy. It's just passing on the link to my email address to my email inbox. I'm going to hit that and open it up. And

here we go. That's the image. So going back to the workflow or to the if loop. So this is what happens if the status is completed. The image is ready and it gets passed on to the Gmail. However, if the image is not ready, it's going to fall into the false loop because the status would now say that it's not completed. It's probably going to say that it's processing. It's going to fall into the false branch. In this case, we want to wait for another 15 seconds or

any other arbitrary weight amount. We're just going to name that wait another 15 seconds. Okay. And I'm going to hit execute step. In this case, nothing is going to happen because it's under the false branch. 15 seconds. And after we wait another 15 seconds, what we want to do is to loop it back to the get node or the HTTP request node here. If the image is not ready, the status is going to say incomplete or in progress and that's going to fall into the false branch and

it's going to wait 15 seconds and it's going to try to get the image again. And then if it's still not ready, what happens is it's still going to fall into the false run. It's going to wait another 15 seconds and try to get it again. And it's going to stay in this loop until the image is ready. And then it's going to fall into the true run and kick it out into the Gmail. Cool. I hope there's a clear explanation on how to build this workflow from scratch. In the

next section, we're going to build a texttovideo workflow where is somewhat similar to what we've built here with the exception that it's going to generate a video for us. I'll see you there. In this section, we're going to build a text to video workflow, which is similar to the previous section, which was a text to image workflow with some minor but important distinctions. Now, just like the previous workflow, we're going to start off with a chat trigger so that you can pass on the

specification of the video that you want to create and that's going to be passed on to a video prompt pigeon instead of an image prompt pigeon. This time we're going to do a text to video model on V3. in your labs, you're going to already have these two nodes set up. And again, the only difference in this case from the previous node is the system prone that we've pre-populated in the video prom agent. So you don't have to. So if you toggle the expression, and I'll blow it up so

you can see it. It is now saying that you're an expert tech video generation prom engineer working inside an automation. And again, you can generate this yourself through GPT or any LLM of your choice to act as a prompt engineer. I'm not going to read the whole thing, but it is pretty similar to the text to image generation prop engineer before. Now, continuing to build the workflow, the next node that you want to hit here on your labs will be the HTTP request node again.

And this time, we're going to waste feed and explore models. We're going to type in VO3 and we're going to filter out text to video category only. And as you can see, as you can see, there are two models here. V3 fast and regular V3. In this case, we're going to pick V3 fast. >> Google V3 Fast is now on WSE AI. It'll blow your mind and go try it now. >> So, just for a warning for V3, it is pretty expensive to run. And as you can see, the request itself will cost me $3.20 per run,

but as you can see from the sample video, it is pretty high quality. So, let's try it out.

So, toggle to the API documentation section. And what you want to do here, very similar to what we've done in the past section, is to copy the entire curl command and go back to the workflow. We're going to import the entire curl command here. And again this is a post method and we're going to say waste post for the name of the node authentication. We've set it up earlier in the previous section. So we're going to just select the same generic header off with waist speed credential demo

and we're going to toggle off the send headers and focus on the send body section. And just before I complete set this up, I'm just going to populate the previous nodes just by saying create a video of of five gorillas on a boat having a great fishing trip. Okay, so I'm going to type that into the chat note. It's going to pass it on to the video prom agent. And let's check out what's the output from the video prom agent. It says a lively cinematic scene of five gorillas on a wooden

fishing boat in the middle of a sunlit lake. Laughing cheering as a reel in big thrashing fish splashes of water in a golden sunlight. All right, looking pretty good. Uh, so let's try that out.

And we're going to open up the HTTP request node here. Going back to the JSON body section of the way speed post node. What we want to take a look here, as you can see, there are a couple parameters that were not mapped correctly. And this sometimes happens when the curl command either wasn't formatted correctly or wasn't parsed over in the correct way. So, in this case, what I want to do is I'm just going to use JSON um the raw body JSON. And in this case, I'm just

going to copy the entire body of the JSON curl command and go back to the workflow and paste the entire body. And from here, essentially what I can do is I'm going to replace this with the string content from the video promotion. Right? So I'm just going to delete that. And I'm going to drag this again. I need to toggle this expression. Let's blow that up and drag this content over in between the prompt. And you can take a look at the right hand side for the

result, which is yes, the prom is now a lively cinematic scene of five gorillas on a wooden fishing boat in the middle of a sun lake. Cool. Aspect ratio, duration, and whether or not to generate audio. And these are formats and configurations that you guys can decide based on your requirements. But this is good to go for now. So I'm going to hit execute step here. And as you can see, the post request is successful. So, as what we've done with the image generation workflow, what we want to do

here is to wait 15 seconds. And we might need a little longer than that because it's a video and it's high quality as well. So, it might take longer than 15 seconds, but we're just going to put 15 seconds for now. And we're going to execute stat to populate that. Of course, what I want to do is to pin this data here. Again, it was is quite costly for me to run the API call. So I want to make sure that I don't have to repopulate this data again and again. So the wait 15 seconds is done. The data

has been parsed through. What we want to do now is to introduce the HTTP request get node. And again going back to the API documentation here. I'm just going to copy this. I'm going to import curl the entire thing. and it's going to just configure all the fields that are required here. I'm going to toggle this to expression and the same thing as we did before, we're going to replace this request ID with the video ID so that it knows which video to fetch as a result.

And then in terms of authentication, we've already set it up before. So, we're just going to pick the same one. Toggle off the send headers part because we already done the authentication on the previous bit. Rename this to waist speed get and I'm going to hit execute step. So as you can see the status has been completed. So we can actually go over to the next node. But before I do that, again, just as what we've done in the image generation workflow, what we want

to do is introduce an if loop because just in case that we run the get API and the status is not completed, meaning the video is still processing that the workflow doesn't all break down. Right? So, we're going to drag the status here and we're going to say that if it's equal to completed that it is true. So, we're going to execute the step and there we go. It goes to a true branch. But what we're interested here is that in the case where it's not true, which means it's

not completed, that we're going to wait for another 15 seconds.

All right, I'm going to set that as 15 seconds. Okay, and we're going to loop this back to the get HTTP request node. And what essentially we've done is that in case when the status is not completed, it's going to go into the false branch. It's going to wait another 15 seconds and it's going to try to get the video. And if it's still not done, it's going to fall under the false branch. It's going to wait another 15 seconds and try to get the video again. It's going to go in

a loop until the video is ready and becomes true. And then we can kick that out to a Gmail note or a Telegram node or whatever node in terms of output that you want to send it to. All right. So then going to configure this send a message again. It's going to be the same thing as before.

I'm going to name it video generated on this particular time. I'm going to give it a time stamp. Drag the now variable. Whoops. Toggle that expression. Drag the now variable here. And there we go. We're just going to do text here because I only want to pass the output, which is this one over here. Okay.

And I'm going to hit execute step. And there you go. Message sent. Let's look at our email and check out the video. So, this is the video link. I'm going to click on that. It's going to download the video. I'll open that up. Okay.

All right. So, that was a video. Probably could have done better with the prompt for the videos. Could have told it to say something or do certain actions and stuff like that. And of course, if you have any particular requirements in terms of the style of the video, you can always tell it that. Right now, it's still a little 3Dish to me. So I definitely can do a bit better. Of course, this is V3 fast. If you want higher fidelity, you can definitely pick a higher model like just a full V3. But

again, it is rather costly. V3 is one of the costliest model out there for video generation. So alternatives to that could be CDAN or cling or want which are model that available in the same platform which is wavepeed.ai and of course a lot of other platforms as well. So that's a quick build along for the text to video workflow. And in the next section, we're going to do an image to video workflow just to complete the whole set. And we can explore how to actually implement or use that in a real

life use case such as a marketing use case or just for fun. See you in the next one. So in this section, we're going to build an image to video workflow from scratch. Just because for an image to video workflow, we're going to need two inputs. One being the base image that the video is going to base off. Second being the video generation prompt that we want to send over to the video generation model so that it can effectively craft videos based on the image as well as your requirements and

specifications. Because of the multivaried inputs that's required here, we do need a centralized way that we can communicate with the workflow. In this case, a platform that we'll use for this demo is Telegram or any other communication platform that you spend most of your time on. So in this case, for this workflow, it gets triggered by either one of two things. It could be a Google Drive trigger, which is when you might upload an image like this into a designated Google Drive and that would

trigger the event and the workflow and that's going to send a Telegram chat message to you saying that an image has been uploaded and please provide the video idea that you want the video to look like and you can chat basically to the bot from this Telegram chat saying create a video of a cat jumping through the hoop based on this image and parachute opens to safely land the cat. So essentially when you reply to this it would then activate the second part of

the workflow which is a telegram trigger and it's going to kick that input into open AI. So in this case a video prom generator that will pass the video prompt to CES API which in this case we're going to again use waistfeed as a platform that will provide the services. So it's going to make a post API call based on the image that we have. And the way it would do that is as you can see in the first part of workflow after we've received a telegram message. What the workflow does it also uploads a

particular image ID onto a Google sheet. And in this node, the agent basically dips into the Google sheet to get the latest URL in case you have more than one image and pass both the video prom and the image URL to Cance post API. And then the rest remains the same, which is a wait note followed by a get HTTP request with an if loop just to make sure that it doesn't break down in case the video has not done processing yet. And then when it's done processing, it's

going to kick it out to either a Gmail, but this case, I think it might actually be better if we just replace this with a Telegram node. So there you go. We're going to build this from scratch because it's an entirely new workflow. So let's jump right into it. So the first node you're going to start off with is the Google Drive note. And the trigger we want to pick is basically on changes to a specific folder. And essentially what this note does is going to monitor the

folder every minute to detect any changes to that folder. And the changes that we're talking about specifically in this case is an upload file. So this is when you drop a photo into that specific drive. Right? So we're going to pick in this case I have a folder ready which is called image to video codecloud. All right. So I'm going to pick that from the list and watch for file created. Right? So I'm going to click on fetch test event and because initially we I've

already uploaded a file just a minute ago. It's reading this as a trigger with the corresponding output payload. As you can see, there are a couple of data here, but where we really want to pay attention to is a web URL link which is publicly available and the variable title is web content link. So, this is the link that we'll be most interested in. And just so that everything works well, we want to make this publicly accessible. So, make sure that you change the settings to be publicly

available at least during the testing period. So the second node that we want to introduce here is a telegram node because what we want to do essentially is when a photo has been dropped into the folder, we want to get a notification on the telegram chat. So this is a simple send a photo message on telegram and I already have my telegram account set up but I'm going to show you very quickly how you can do that on telegram and what you want to do is type in on the search bar on top here

botfather and you want to make sure that it's the correct one which is the one with a blue tick and it's going to lead you to this page. And what you want to do is hit on start and it's going to have an automated/start uh message here. And what botf father is a place where you create your bots within telegram. And this is not to be confused with the air agents that we're creating on nn end. This is simply a bot that listens in to the communication within telegram and be able to pass on

that as a trigger to your end workload. Now in this case I'm going to create a new bot. So I'm just going to choose a / newbot and I'm going to need to name the bot. So I'm going to say end it in test demo one and I also need to give it a bot name. So the same thing I'm going to add it a bot. So there you go. This is a link to chat with the bot. The bot has been created and this is the API key that we can copy. So I'm going to click on that. I'm going to go back to my

workflow and in this case I'm going to create new credential under telegram. I'm going to name it telegram demo. And I'm going to essentially paste the access token here and hit save. And there we go. We're going to look out for the green bar here. So connection has been tested successfully. All right. So now that's connected. The other configuration of the fields that we want to do here is to fill in the chat ID. And for the chat ID, what we want to do here is we want to call another telegram

trigger, which is the second trigger that will activate a separate part of the workflow where then you can input the video ideas that you want into the workflow. So in this case, I'm going to scroll down. I'm going to go to triggers and then I'm going to pick the onssage trigger. So the credentials that it's connected with is Telegram demo which is the same credential and the trigger is on message. I'm going to hit execute step. As you can see it says there's problem running the workflow. Please

resolve outstanding issues before you activate it. It has nothing to do with this node because as you've noticed the problem actually lies in the other node that I was setting up halfway. So I didn't finish it because I needed the chat ID and in order to get the chat ID, I was going to use a trigger note to call the chat and then paste the chat ID over here. That's what I was trying to do. But so in the in room what I'm going to do, I'm just going to fill this in

with a dummy content which is just a string which is a test test and that should solve the issue and let me run this node. Right? So I'm going to execute step and it's waiting for a trigger event. So I'm going to go back to my telegram chat and again I'm going to click on this link. So it's going to lead me to a chat with the bot and I'm going to say test. Oh, okay. So let's start. So, so as you can see, it's capturing the very first message here. And because it was just a

test workflow, it stops after the first iteration. So, the first iteration was / start is not capturing the second one, which is the test here. Cool. All right. So, let's head back here. And so, that's the Telegram trigger. Let's get the chat ID here, which is the one here. And because this is going to be the same chat ID throughout, as that's the way you would communicate with the bot. So, I'm just going to copy the chat ID here, which is the ID of interest. And because

this is going to be the exact same chat that we're going to communicate with this workflow, I can just basically copy the ID and paste the ID hardcoded into my chat ID here. So it doesn't need to be dynamic. All right, cool. So we want to drag now the photo variable into this field. But again, because I ran the Telegram trigger earlier, it is now rewriting my previous node, which is the Google Drive trigger node with nothing. So, what I want to do is just go to executions and go to my very first

execution. And as you can see, this is populated with the previous data. And I'm going to copy that to editor. And now it's going to populate this. And then what I want to do is go to the Telegram node. And I'm going to drag the URL of the image that rests on the Google Drive. So, we're going to scroll right down here. And this is basically the URL that is publicly available now that I have shared the permission to anyone being able to be with the link. So I'm going to just drag this into this

field. And what I want to do is also just add a caption to this because what I want to say is you've uploaded this photo to the Google folder. Kindly provide the video idea that you want to generate from this image. Okay. So, I'm going to just blow this up so that you can see it. You have uploaded this photo to the Google folder. Kindly provide the video ID that you want to generate from this. Okay. Type here from this image. So, cool. I'm going to hit execute step

and see what it does. So, all right. It's sending uh some type of stuff into my Telegram chat. So, let's see. Now, it's saying this. is sending me the correct image which is the cat going through the hoops. It says you've uploaded this photo to Google folder. Kindly provide the video idea that you want to generate from this image. Perfect. So that's how I want to be notified of any photos that anyone or myself have dropped onto the folder. So I'm going to just move this up. And the

next node just finishing this cart workflow would be a Google sheet node because what we wanted to do is we wanted to append a row in sheet or rather log the information about the photos that have been uploaded into the Google sheet. Right? So this could be we're going to name it image log. All right. So it is simply logging it to a sheet that I've created here which is called image to video log and it's just a simple two column sheet. The first column being the image URL. The second

column being the date when it was uploaded or created. And I'm going to make sure that the sharing permission is public as well. And I'm going to head back here and I'm going to choose from the list image to video log. So there's only one sheet there. So it's going to be sheet one. And it's going to read out the two columns which is the image URL and date. For the image URL, what we can do is that we can go to the Google Drive trigger and drag the same web link from

Google Drive and just paste it here. And for the date, we want to scroll down to variables and we're going to drag the now variable. All right. Cool. We're going to hit execute step. All right. And then we see that now the second image has been uploaded at this at this time. Cool. All right. So that's done. That part workflow is completed. What we want to do now is to move on from create a video agent. And in this case, I'm going to use open message and model

node. And this is essentially a video agent. And I've got my open air account already connected as before. I'm going to choose the model here which is GPT 4.1. And again I want to execute the previous node. Okay. And right now it says test not very meaningful for me to run the test run. So what I want to do is I want to open up the node and execute step so that it can get new information. And then I'm going to go back to my Telegram chat and I'm going to create a video of a cat jumping

through oops of rainbows and opening up a parachute towards the end so that it can land safely. Okay, so I'm going to send that message through Telegram. As you can see, it's getting the text which is create a video of a cat jumping through hoops of rainbows and opening up a parachute towards the end so that it can land safely. Cool. Okay. So, let's go back to the video prompt agent. Now, this is populated. What I want to do is I want to direct this text into the

prompt field here, which is the user prompt because that's the video ID that it's going to work on for it video prompt. So, next thing I want to do is I want to define the system prompt for this node. And again, it is pretty similar to the previous sections where it was a text to image or a text to video model. And you can definitely make use of tragic PT to effectively create and craft the system message for a video prompt engineer. But what I want to show here is I'm going to blow this up, put

it on expression so that you can see is the output format. So this time I didn't put in much effort in terms of trying to really prop engineer the system message. So as you can see there are two main tasks for this particular node which is the first one being create an effective video prompt to a prompt video generation model based on users input which is great and then the second one is to make sure that the output is separated into two JSON objects which is

what the next node is going to expect from this particular node. And the first one being the video prompt itself which is going to be in strings. And the second one is the image URL which is the image that the video generation model is going to create a video based off. And in order to fetch the image URL, we need to make sure that we're attaching the right tool for the agent to look at. And in this case is a Google sheet attach tool. And what I want to do is write to

get rows. And from the list is going to be the same image to video block sheet. And we're going to pick the only sheet that exists in that project, which is sheet one. And there we go. So essentially what I'm telling it is to go back to the system prompt again that is going to fetch this value from the last row of the attach Google sheet locked. All right. So we just want to name it just for clarity. Google sheet lock. Okay, cool. So we're going to run this and execute the step and see what the

output is. And again, even though we have already specified the output in the system prompt, we just want to make sure that we toggle on the output content as JSON just to make sure that it's outputting it as two separate JSON objects. And as you can see under the content here, there's the prompt strings and the image URL strings which which are the two expected parameters in the next node. So the next what we want to do here is just a HTTP request node. And

again, we're going to import curl here. Go back to waist speed and under models this time what we want to do is we want to check the category image to video and there are a couple of options that we can choose from but in this case we're going to choose the first one which is Cance version one. All right cool uh and we're going to toggle into the API docs. Copy the curl command which is the post method here. Go back and essentially paste the entire thing and it's going to

configure everything here. Authentication we've set it up previously. So we're going to just choose the same authentication here. And for that we can toggle off the header part because the authentication has already been included in the credentials. And what we want to change here the same thing we have couple parameters that we can set that has relation to the type of videos and what kind of requirements that's required. But what we want to do here is we're

going to just change the image URL. Drag it to this value here. And under prom, we're going to replace that with the prom strings and also drag it, drop it here. We can specify the duration. I think 5 seconds is good for now. But yeah, bunch of other stuff that you can configure as well. And then we're going to remake rename this to cens. And we're going to hit execute step. And there you go. The post request is successful. And as always, we want to wait

until the video is ready for us to get. Right? So, we're going to change this to 15 seconds. I'm going to hit execute step. And as that's running, we're going to introduce the get HTTP request node. See, that's get. And again, for this, we're going to go back to the documentation and copy the get curl command and just import curl. Paste the entire thing and it's going to be configured. And as usual, we're going to replace this request ID with the ID that we got from the weight node earlier. So

I'm just going to paste it there. And authentication, same thing. We're going to pick the same credentials. We're going to toggle off the headers here. And we're good to go. So as you can see, it's waited 15 seconds. And we're going to try to get and the status is completed. So that's good. So 15 seconds was enough uh to get that. But just in case again, um that's not ready yet. We want to make sure that workflow does not break. So we're going to pick the if

node creating an if loop. So we're going to say that if the status is equal to I'm just going to copy and paste make sure that it's word for word the same completed then it's going to fall into the true branch and it's going to go to the next node. But in case it's not completed it's going to go into the false branch. It's going to wait another 15 seconds. Right? I'm going to execute a step. Actually it doesn't matter because it's going to fall into the true

branch. I'm going to reconnect it back to the get requests because in case it's not ready yet, it's going to wait another 15 seconds. You got to try to get it and it's going to wait another 50 seconds and try to get it again until it's ready. So, in this case, it's already done. Uh, what we want to do is to just move on to the next node because it's true. And the next node that we're going to append here would be the Telegram node. And this is going to send

a video node. Telegram send a video. And again, chat ID, you know, it can be dynamic or you can just hardcode it into the thing. But in this case, because I already have it plugged in, I can just drag the ID here. In terms of video, we're going to get it from the if node. Got the output right there. Going to drag it in here. Okay. And we're going to hit execute step. All right. As you can see, sending over some stuff on the Telegram. So, let's go to Telegram and

check it out. There we go. As you can see, there's a video of the cat jumping through the hoops of rainbows and parachute opens and it lands safely. Cool. All right. Of course, a lot of things can be done again with the prompt. We could define what kind of style we want it to be. This is a bit more cartoonish. If we want it to be hyperrealistic, that's possible as well. So, we just need to include all of that in the system prompt. All right. I hope that's a clear build of the image to

video workflow. So, in the next section, you're going to practice building it from scratch yourself in the labs and I'll see you in the next one. And just very quickly before we go, I just want to point out that I'm building this in one single workflow or one single worksheet. Um, but what you can do, you can actually separate these two workflows into two separate worksheets and it'll just make it much easier for you to troubleshoot and iterate as you go. So just in case if there's any error

and the workflow is bugging out or erroring out, you can actually zoom in to any one of the workflows that are bugging out instead of looking under the hood for these two workflows at a go. So if you separate it into two workflows, you're going to know which workflow is working down and you could go into the relevant workflow and find out what's not working within the notes. With that, I'll see you in the next section. In the previous section, we talked about how we

can access way speed API to call on text to image or text to video generation model like V3. Now, obviously that's not the only way to access V3. And perhaps one of the most straightforward way is to access it through the Google Cloud Platform itself. Now, the way you can do that is to go to cloud.google.com/vertex-ai and go over to the documentation. So, Vert.Ex AI is a place where V3 is hosted on Google Cloud. And in the documentation, you can scroll down to

the full HTTP request with which you can populate the HTTP node to call on the API. Now, in order to get started, you can actually go down to the simplified version in the sample request. Let's go back to the workflow now and build a simple workflow where we can call on the text to video generation model in V3. So, the first node that I'm going to call on here is just a simple trigger manually node. And the reason for that is because we just want to try the HTTP

post node and make sure that everything works well before then we can replace a trigger node with something that actually populates the API calls with a prompt and all the information that you want to pass on to via 3. So we're going to run this node just to populate it. So the next thing we want to do is we want to obviously call the HTTP request node here and the method that we're going to choose is post. We're going to go back to VO on Vert.Ex AI API documentation.

So, what I want to do is go down. As you can see, there's a whole HTTP request curl command here that you can copy and paste. However, it's got a lot of stuff that I might not necessarily need to configure for my videos, at least not at the start. We want to keep it simple as this is the first run of the demo. Just want to let you guys see how to set it up simply. So what we want to do here is to scroll down a little bit further and you see that there is a sample request

that we can copy right here and this is the URL endpoint which we want to copy and let's go back to the credential here and we're going to copy the URL and there are two things that we need to configure the project ID as well as the model ID. So in fact what you can do is you can configure this directly from the Google cloud console. For example, if your project ID is naden- ak-demo the project ID you can get from your Google cloud dashboard. It's not the project number is a project ID. So you

can just copy this and go back there. Actually I mistyped that. It should be demo-k. And the second thing you need to configure is the model ID. And you can scroll up and see the different types of model ID that you can choose from here. So in this case, I am going to just copy VO3 fast generate the 01. There we go. I'm just going to copy that and go back. Actually, I'm just going to just paste the entire thing and we're good to go. Delete the post. And there we go. That's

the URL right there. Now, the way the authentication is done is going to be different from the way we would call platforms like way speed or any other platforms that uses the typical header off API. With Google Cloud, what you want to do is you want to choose predefined credential type. And under the credential type, there's a specific credential that you want to choose which is Google OOTH. So that's Google O2 API which you want to choose. And right now I already have an account set up. But

what you want to do is to create a new credential. And as you can see, it's very similar to the way we've set up our OOTH earlier. You have the OOTH redirect URL here, which you have actually already pasted before in the Google Cloud Console. But just to make sure it's the same URL, you can do that. But what you need to grab is the client ID and client secret. So, what you need to do is just simply go back to your Google Cloud Console and go to credentials and go over to your client IDs here and

you've got your client ID. Paste that in and go back again for your client secret. And depending on the setting, sometimes your client secret will be unavailable once you've created them and you're supposed to copy them and store it somewhere safe. So, if you set this up previously and you stored it somewhere, you can use the same client secret and paste it into your end credential. However, if you haven't, what you can do is you can delete this and add another secret. So that's an

option as well. So again, as you can see, there's authorized redirect URLs here, which is essentially the same with what we see on the NN credentials right here. And we're good there. So we're just going to paste the client secret there. And just before we go, this is where the first run, the way we set it up in the OT previously, we need to add a scope here. So essentially, the scope grants the bearer all the services in the Google Cloud Platform that is authorized by the IM. Since Vertex AI is

part of cloud AI platforms APIs, it requires an OA token with this scope in order to accept the request. Now again, before we go back to the workflow and do that, what you want to do is you want to make sure that you go over to Vert.ex AI API on your Google Cloud console and make sure that you enable this API. And once you're done, you can simply click sign in with Google and it'll lead you to a login page. And what you want to do is just allow the access and you're good to

go. So you can see the green bar shows up and the account is connected. So you can toggle out now. And what you want to do now is toggle over the sand body section. And this time we want to choose use JSON body. And using JSON body, we're going to just go back to Vertex AI and copy the entire JSON body which is the simplified version here. And even before you do that, you can configure a couple things in in terms of the prompt for the video and the output to the

storage URI if you are using the GCS bucket and you want the video output to be stored in that bucket and the sample count. So I'm going to take that but at the same time I'm going to configure a couple of fields as well such as the aspect ratio as well as how long I want the video to be. And I'm going to just paste the entire trunk here so you can see. And it's basically similar to the simplified version. is just that I've added a couple things such as the aspect

ratio and the duration of the video and I have actually removed the storage URI because I didn't set up a GCS bucket and basically I just wanted to return the video in B 64. So if you remove the storage URI Vertex AI is going to output the video in B 64 format back to end. So now that's all set up what I want to do is just hit execute step and there you go. I've got a name here and basically this is sending over to Vert.Ex text AI and VO3 is generating the video as we

speak. What we want to do next is sorry, let me just rename this V3. Okay. All right. And we're going to wait for 15 seconds. Going to run that. And essentially what we're trying to do is we're waiting for the video to be generated before we pull for the result. Right? And we're going to create another HTTP request node as that's waiting all for video from text. All right. And the method is also a post in this case. And essentially you can get the endpoint URL

from the pull long running operation right here in the same documentation. But I'm just going to go back and paste the entire URL here. And under authentication is the same thing. Predefined credential type. We're going to pick the same credentials with the same account under the body. This one's going to be simpler because we're just getting the results back. And basically, we just need the operation name.

And we're going to hit execute step. As you can see, it's got an output, but it says the unsupported output video duration 5 seconds because I specified it to be 5 seconds. So, supported duration are eight for text to video feature. So, I'm just going to go back and change this to eight. All right. So, I'm going to rerun this. Run this again. And we're going to hit execute step. All right. So, we're getting an output here. And it says that the node contains 6 MBs of data. It's going to slow down

the browser temporarily, but we're just going to hit show data here because I want to show you the entire format of it. As you can see, because we didn't specify a bucket for the destination of the output, it's actually returning a base 64 format into nen. Now what we want to do next is obviously convert this into binary. So we can download it and do with it whatever we want. Send it over to whichever platform, email etc. But here what we want to do just before

I move on is to introduce an if loop as usual because we want to make sure that just in case the status isn't done that it's going to go into a loop and try to fetch it when the video isn't completed. So I've actually picked the wrong type there. So it should be boolean. We're going to make sure that when it's true, which is, you know, it's done, that that goes into the true branch. And if it falls, it goes into another wait note. And this is going to be wait another 15

seconds. All right, it's running again. And we're going to loop this back to the poll. I'm going to run this. Anyway, it wouldn't run because in this case, it shouldn't run. It should fall into the true branch. Yep, there you go. Goes the true branch goes green. So this is going to a set for edit field note because essentially we want to set this output which is B 64 to strings. We're going to just call this B64 and we're going to hit execute step there. And the output

is rather large. This is coming back as strings. And the last step here we want to do is to convert file. And we're going to pick move B 64 string to file. So there we're going to hit show data there. We're going to drag this parameter right here into B 64 input file and we're going to output the file as just a typical default name data. Going to hit execute step there. So, as you can see, we're getting an output here which is a data. Now, we can just download the file and that's essentially

the video. Let's open that up.

All right. So, we've got now a serene walk down the beach. It's a good video by VO3. As you can see, the audio comes with it as well. Looks pretty good. Yeah. So, we've got the output here. And what you want to do with the output, obviously, you can upload it to drive or just try to send it somewhere. But this may not be the way you want to download the video exactly from Vert.ex AI. But what I want to show is just the way that you would set all of this up and be able

to call Vertex AI and the VO3 model to generate text to video through this workflow. Of course, the easiest way is to create a GCS bucket and just put the destination storage as that bucket so that you can just retrieve it from there later on. This is just a simple build to let you guys know how it all works. But there are a couple of reasons why we're using platforms like misfeed AI instead of just Vert.ex AI. The reason for that is because there are other models that

potentially we want to use. Again, VO3 is one of the costlier models even though it's one of the best out there in producing high fidelity videos and audio. But for everyday use models like Cance and one and cling might be more suited to your use case depending on your needs. So for that reason platforms like way speed or foul and there many other platforms like that actually provide an easy onetop platform where you can access all different types of models without the need of setting up

all the credentials and API calls just to access that particular model. Hope this is a good explainer. I'll see you in the next section. Now, let's quickly talk about a decision you'll face when starting out with nitn. Should you use nitn cloud or should you self-host it? Both have their perks and a few trade-offs. Starting out with nitn cloud gives you the benefit of simplicity. You just sign up and start building. No service, no docker setup, no headaches.

Updates and security patches are handled for you. So, you're always on the latest version as long as you updated on your admin panel. Plus, if you run into trouble, you've got official support and uptime monitoring already built in. But the trade-off, cost and control. With cloud, you're paying subscription. And while it's worth it for convenience, you don't get full control over the environment, and you're limited to the TSM resources that N&N offers. On the

flip side, self-hosting means you get total freedom. You decide how much power your instance has, where it's located, and who has access. It can be much cheaper if you already have a server space or even want to run it locally for personal projects. and you have the flexibility to integrate with internal tools and databases that you might not want to expose to the public cloud. To me, this is probably one of the biggest positive points of self-hosting is that

for some companies and businesses, it's simply not a choice, but a security requirement to make sure you host it in the service. They're not exposed to external environments. But again, the drawback would be maintenance. You're in charge of keeping the server alive, updating addit, and handling security patches. If something breaks, there's no safety net, and you've got to fix it yourself. So to sum it up, choose ended and cloud if you want the easiest path to get started and don't want to deal

with infrastructure. Self-hosted if you want full control, tighter integrations, and airtight security. Honestly, there's no wrong answer. It depends on your use case. And if you're just learning, cloud is usually the fastest way to go. But if you're building production workflows and want flexibility, self-hosting gives you the keys to the kingdom. I'll see you in the next one. This section we're going to cover the sub workflow tool and how we can use it to segmentize complex

workflows into easy separate segments so that it's simple for us to troubleshoot and iterate on. Now in this case I'm going to take the workflow that we've just built in the previous section which is the image to video workflow. And there's a different architecture in the way we built these workflows. And I've said previously the current workflow has two triggers in one single worksheet. And that might not be ideal for error handling because when the workflow errors out, you have to go

into both the workflows to check which node that the error has occurred in. Now, one way to do that is to split the workflow into two. So in this case, I'm going to take this as the main workflow. As you can see, the trigger is a Google Drive trigger, which is triggered when a photo was uploaded to the drive. And once triggered the next note, it's going to send a telegram message with the photo from the drive and ask users for the video prompt or the video ideas that

user want to generate the video based on this image. And after that, it's going to lock the image URL in the Google sheet. Now, what we're going to do here is we're going to add a execute subworkflow node. Essentially, I'm going to show you how to set that node up and how it links to another workflow and how the entire logic works when it comes to the interface. So, in this case, when you choose an execute workflow node, you're going to have to choose which workflow that's

going to activate or trigger. And in this case, you can't actually just choose it from the list. And here, I've created another workflow and I've called it sub workflow demo. Essentially what it is is a copy paste of what we had in our image to video workflow and just the top part and we're going to edit that later on. So going back to the main workflow after you created the sub workflow you can simply choose that from the list

and essentially it's going to call the sub workflow whenever this workflow is triggered right after it logs the image URL into the sheet. Now what you want to do here is to go to the sub workflow. In this case we're going to replace a trigger node to a execute subworkflow trigger. And as you can see it says here when executed by another workflow. So we want to choose that one. So there are a couple things that you can configure when it comes to how you want the information from the main

workflow to be transferred to the sub workflow. Now, in this case, we're just going to choose accept all data for now, just to show you the distinction of what happens when you configure the data. All right. So, I'm going to take this I'm going to and I'm not going to plug it into the rest of the workflow just yet because I just want to show you what kind of data would be populated when this workflow is executed. So, let's try to run this workflow and see what we get.

All right. So the execute workflow has run successfully. And one thing about the sub workflow trigger is that when a workflow is triggered by another workflow, you don't actually need to publish it here. And as you can see, it says that the execute workflow trigger does not require activation as it is triggered by another workflow. So cool. So we're going to hit executions here. to see the logs of the execution.

As you can see, I've executed the main workflow and it's receiving data here in the in the trigger workflow. I'm going to hit copy to editor so that I can see what kind of data has been populated for this node. All right. So, I'm just going to blow this up slightly so that you can see. So what I've done is I picked acceptab all data as the input data mode and essentially the data that's been pushed forward is the image URL and the date. So these are the two data points that's

coming off here. And that's in part because the data point that we've received from the previous Google sheet node in the output payload. We're only saying two components that are being pushed out which is the image URL and the date and it's simply passing those to the other workflow. So if you want more information to be passed into the next workflow, well then you're going to have to configure the note to make sure that it's passing on the relevant information that you want

to the other workflow. Now going back to the other workflow, I'm going to just push this back a little bit. And in this instance, we want to choose define using fields below just to see what the difference is between accept all data. And when we choose define using the fields below, we want to make sure that we define the fields. So for example, in this case, we want the image URL as one of the data, right? And let's say we don't really need that and we don't really care about

it. Okay, so we're only specifying just the image URL. So let's go back to the main workflow and this time we're going to only run this execute workflow node and see what it sends across to the subworkflow. So as you can see, node is executed successfully. Let's go back to the subworkflow and check the execution logs. As you can see, there's a new one coming in here. And we're just going to open that up. Now, you see the difference is that it's only going to output the data in the

format that you've defined here. So, we've defined the image URL field only as strings and it's only going to pass that data property in the output payload, which means the date output is not included in the payload here. So that is a main difference when you're defining using the fields below as opposed to just accept all data. And this is extremely useful when you want to format the input in a specific format or in a specific way in the next node for the rest of the workflow.

So all right, so let's go back to the editor. In this case, we're going to change back to defined using fields below, but we're going to add in this case the date variable as well. I'm just going to hit execute step again. And there we go. There no inputs data. So what it's doing is it's outputting these two variables with no content inside. Cool. All right. So now when we look at the architecture, what's going on here is that the two workflows are activated when a photo is uploaded on Google

Drive. The user is notified on Telegram that a photo has been uploaded together with an image of the photo and that image is then logged into an image log sheet and then the sub workflow is called. So in the sub workflow, this trigger is the start of the entire chain of workflow here. And what we want to do in now is to chain it up with the video prompt agent here. Want to do just before we chain it up with the video prompt agent here is we want to add a telegram note. And if you

remember what we need to do is we want to get a text input from the user describing what they want to do with the video. just an idea on how they want to generate the video because they don't need to come up with the entire prompt. We already have a video prompt agent as part of the workflow. They just need to tell us directionally what they want the workflow to do for the video. So in this case, we're going to select the send message and wait for response node.

So we're going to make sure that we pick the right Telegram account. And in this case, I'm just literally going to go back to the main workflow. I'm going to copy the chat ID because it's going to be the same chat ID that we use. Right? Again, you can make this more dynamic by passing it through the execute workflow node and passing it into the sub workflow. But in this case, because it's going to be the same chat, I'm just using I'm just hard coding it into the fields. So now the previously

the telegram node will show the photo to the user and say that you've uploaded this photo to the Google Drive. Kindly provide the video ID that you want to generate from this image. So, we're we don't need this part anymore because this is just going to be a notification message. Instead, we're going to have the message sent here in a subwoofer. So, we're going to make this a question, which is could you provide the video ID that you want to generate from this

image? Question mark. And we want the response type to be free text. All right. Cool. So I'm going to hit execute step here just to see what we get on the telegram. And as you can see the message that we got from telegram is could you provide the video idea that you want to generate from this message. All right. And there's a respond tab here which I can click on. I'm going to open that link and basically type in my response for the video generation ideas that I want.

So create a video of a cat flying through hoops of rainbow and landing on a field of sunflowers with purple unicorns running in the background. All right. So, we're just going to do that and hit submit. And cool. All right. So, let's go back to the workflow. And as you can see, receiving, and this is kind of hard to see, but I'm going to just drag this to the left a little bit. Um, as you can see, the input that we're getting is create video of a cat flying through

hoops of rainbows and landing on a field of sunflowers with purple unicorns running in background, which is a text that we've input into the field there. Cool. All right. Okay, so we've got an output data here and what we want to do now is to chain up the output. And let me just blow this up again so that you can see. So we're going to chain that up with the video prompt agent. And now we're going to have to configure this very quickly and just drag the text

from the telegram again. Drag this here to the right. the text which contains the video ID into the prompt here

and this is going to be the user prompt. Essentially, in terms of system message, it's going to be the same because we still want it to create an effective video prompt to prompt the video generation model based on users input and also to output only the following two values in JSON format which is the prompt that it generates as well as the image URL that it fetches from the Google sheet. So everything else stays the same in terms of the rest workflow. The only difference is we've now changed

the trigger to this workflow from a telegram onssage trigger into a executed by another workflow trigger. So the rest of the workflow is going to run the same. And what I'm going to do now is I'm going to do a top to bottom run of the master workflow and the sub workflow as well. So I'm going to hit save here and I'm going to hit execute workflow here. It runs the execute workflow and it's spinning. The reason for that if we go back to the telegram, it says that I've

uploaded this photo which is correct. And again, it says, could you provide the video ID that that you want generated from this image? All right. So, I'm going to respond here. It's waiting for my response. And again, I'm going to say create a video of a cat flying.

Oops. of rainbow and landing on a bed of sunflowers with purple unicorns running in the background. Okay, I'm going to hit submit here and go back to the workflow.

It's not showing anything right now, but if you go to the execution logs, you can see that it's getting an input. It's getting a trigger and it's running the workflow. So, it might take a little bit because it's going through basically the HTTP API post call to Cance or Way AI and then it's going to wait 15 seconds. It's going to do a get API call and then if that fails, it's going to run the loop again and try to get it again. And once it has the result, it's going to send it

to the Telegram chat. All right, so we're just going to head back to Telegram. As you can see, the video is ready.

And I got to say, this one is not as good as what I expected it to be. probably something to do with the prom, but it's getting the main gist right, which is, you know, the cat is landing onto a bed of sunflowers with unicorns running in the background, but the style is a little bit inconsistent. And of course, that we have to go back to the system problem and fix that. But the point of this is to show you guys the difference between how the architecture could work. Essentially does the same

thing. But the difference is that you have now split the one bake workflow into two separate workflows. And this will help you when it comes to troubleshooting and iterating because you can re literally look into debug all the errors occurring in the main workflow or in the sub workflow. So it just makes your life easier when you're trying to error handle uh if anything goes wrong. I hope that's a pretty clear explanation on how we can use the execute subworkflow note as well as the

executed by another workflow trigger and how it all works. I'll see you in the next section. In this section, I'm going to run you through how to selfhost n on your local machine through Docker Desktop. So, the easy way to get started is to go to GitHub and grab the NN-IO/ selfhosted AI starter kit. And what you want to do is just go over the documentation a little bit. And depending on what kind of machine that you're on, I'm currently on a Mac. So, this is the documentation that I want to

be referring to. As you can see, it's a simple git code and you can get started. But just before you go ahead and do that from your terminal, what you want to do is you want to make sure that you have your Docker Desktop downloaded installed, and if you haven't done that before, what you want to do is to go over to docker.com and basically download the Docker Desktop app into your machine. And I already have my set up here. So, just go ahead and download that if you haven't done so. And also,

you want to make sure that you have Git installed on your local machine. So, once you've got everything set up, and again, I'm on Mac machine. So what you want to do is scroll down here where we're going to clone the entire package together with Olama within because that's the LLM that's going to run on your local NN. And if you already have Olama set up on your machine, there is a documentation separately for that. But in this case, what we want to run is the

command lines right here. And we're just going to copy that to our terminal. And it's basically a git clone. And once we've cloned that repo, what we want to do is cd into the self hosted AI starter kit and set up the environment file. Make sure that it in there. There we go. And what we're going to do now is to do a docker compose command. And this time is the CPU one because this is a max silicone. And once you run that, it's going to take some time to run depending

on how quick your internet connections are. And as you can see, it's downloading a couple of things. You know, Postgress, Quadrron, Nadan, and O Lama, which are the basic building blocks that you need to work with locally. Now, that took a little while, but now it's completed. So, what we want to do now is just to go to the local host here, 5678, which is the default local host that you can access your NAND instance on. So on my browser, I'm going to go over to localhost 5678. As you can

see, it's going to ask for some email credential. Sign up. So you can do any email you want because it's all basically running on your local machine. All right. And once you're signed in, you're going to see that there is a demo workflow because part of the repo there is a demo workflow template that's been loaded up. So you can just open that. As you can see, the template loads up with a basic LLM chain with the Lama chat model. And for this basic chain to work,

you have to plug in a fallback model. So in this case, I'm just going to add another lama model here. Choose the same credential there. Just leave it as that. And basically, we can just say, "Hey, how's it going?" And it's going to access the Oama chat model. And again, all of this is basically being powered on your local machine and is running on the doc desktop. But I'll show you in a little bit what that looks like. But here you go the notice executed successfully and it's responding with

this output. And on the docker desktop as you can see there's one container running which is a self-hosted AI starter kit and under that you can see postgress quadrant and n is running and if you would stop the operation of a container and you head back to edit end instance you can see that the connection is lost here. So it is entirely running on your docker container and powered by your local machine. So going back to our docker desktop here I'm going to hit on start

and on the left hand bar you see there are images and these are images that you can download you know latest versions you can see you can search for nan images and download the latest version of nan and and basically run that and then there's the volumes here which is where all the persistent data is stored and I'm not going to go into the weeds of how it all works together because we do have a separate course for docker to address that but going back to the container if you will want to do any

configuration changes and stuff like that what you can do is actually open up the configuration here and actually configure the doc compose file depending on the kind of requirements that you need such as user credential persistent storage and port configurations. But that's it for a super quick one on how to host edit on your local machine with docker. So in the past section we talked about how we can host nitn on our local machine with docker desktop. And in this

section we're going to go through how you can run nitn on an ec2 instance with docker running on top of it. So an easy way to get started is to go to codcloud.com/playgrounds. So this is where we host all our playgrounds including AWS Azure GCP and Azure data. So what we want to do here is to go to AWS and spin up the AWS sandbox playground by hitting launch now. And it's just going to take a couple seconds to start up the playground. And there we go. We've got

our credentials here. What we want to do is just copy this to our browser. And that's going to lead us to a sign-in page on the AWS console. And what we want to do is to go back to the playground and copy out the username and the password. And you can just fill that in to gain access to the AWS console. And there you go. Got a console ready to go. And what we want to do here is head over to EC2 instance and hit instances. And as you can see, because it's a new

session, there are no instances just yet. So we're going to hit launch instance. And I'm going to call this instance nan-demo. And we're going to choose YUbuntu here. And we're just going to leave everything else as is for now. And what we want to choose here is a T2 medium. And again, this is just to cater for the fact that we're going to have lama as part of the packet that's going to come in. As you recall in the past section when we did the git repo clone, it's

going to be quite sizable. So we just want to make sure that we're catering for that. And of course the storage later on, we want to configure that to be quite sizable as well. So with a key pair login, we can create a new key pair. And we're also just going to call this an demo key. It's an RSA type withPN format. So let's create key pair. And that's just going to get saved in my download folder. And under network settings, we'll make sure that it is allowing SSH traffic from anywhere for

the time being. And at the same time, under configure storage, we want to change this to 30 just to ensure that it's got enough to cater for the packet. Right. And everything looks okay to go right now. So, we're going to launch instance. And there you go. The instance was successfully launched. It takes just about a minute. And as you can see, the instance has been spun up. And right before we go to our terminal to start setting things up, what we want to do is

just go into the instance here and make sure that the security group is configured. So, there you go. We're going to the security tab here and hit the security groups. And under the inbound rules, we would just want to make sure that we add the SSH inbound that's coming from the end port. So this is custom TCP and it's going to be port 5678, which is the default port. And we're going to allow it to be able to be accessed from anywhere. Now, we're going to save rules. And there we go. That's

been added. And going back to our terminal, we're just going to type in chmod 400 and then dash demo- key, which was our p key. So just to make sure that we can gain access with the right pairing key. And we're going to SSH into the instance by typing in this command line which includes the PAM key as well as the Ubuntu public IP address which we can get from the EC2 instance console. and just copy that and go back to the terminal. Paste that in and we're going to run that. So,

this is a typical message that's going to show up for the first time if we're trying to SSH into it. So, we're just going to hit yes. It's going to just double confirm because the key is not known by any other names. But since we're the ones who created the instance, we know that this is safe. So, we're going to hit yes. So, the next thing we want to do is to update the system and install Docker.

We're going to run install there. Next, we're going to enable Docker as well as add the user group. Make sure that we can get access to column Docker. And what we're going to do next is just to install Docker Compose version two. And just to make sure that it's installed properly, we're going to run Docker Compose version command. Sorry. It should be Docker Compose just version without the dash. Oops, there's a typo there. So, should be Docker Compose version.

All right. So, that's version two. Good. We can move on. So, the next few steps are going to be very similar to what we did in the last section when we're trying to self-host on Docker. So, we're going to do a g clone of the g repo. And we're going to change our directory to the self hosted AAI starter kit. Okay. And we're going to copy the environment file. Let's make sure that that's created. All right. And just before we run the docker compost command, we're

just going to do some minor change in the environment file because sometimes the security settings might not allow you to access the destination due to certain types of security protocols. And what we want to do is in this case because we're just trying to show how to set it up is to disable some of that. So, what we want to do here is to just paste in the line edit and underscore seccure cookie equals false. And once that's done, we're going to exit. We're going to hit yes. And there we go. So,

I've just cleared that up. And what we're going to do here is just run the docker compose command and basically to pull in the same way as the previous section all the nan files the packet and everything that's contained in the git repo into the EC2 instance. So it's going to take a little bit of time as is pulling all of that. So now that's done. We want to check if the container is up and running. So, we're going to type in the docker ps command. And as you can see, the containers are

running. So, let's go to a public IP address. And the way you can do that is to go to your AWS console and copy the public IPv4 address. And once you do that, you can simply type it in with the port 5678 at the end. And there you go. That's your Nident instance. And as you can see, uh this is the first time logging in. So there's no persistent data of credentials. So I can just type in any credentials just like this and

it's going to spin up the edit instance. As you can see, this is a dashboard that you would normally see on your end cloud. It's just announced it's hosted on an EC2 instance on AWS. Everything else works the same way. If you go into your demo workflow, the same template is going to spin up as a default demo template which is attached to Olama. And again, Olama was part of the package. So it was downloaded and basically loaded up within the EC2 instance. Cool. So if

you were to go back to your instance right here,

you can see the usage in the instance tab. And that was probably when we were doing the git clone. But of course, as you move on and operate the NDN environment within the EC2's instance, you're going to see the consumption data over here. Okay. So that's a straightforward way to show you how you can quickly set up an EC2 instance and get your end environment connected and hosted on there through Docker. And again, if you're not familiar with how EC2 and Docker works, we do have courses on

that. So you can go and check that out for sure. And of course if you rather just skip all the hassle of not just setting up the environment and the infrastructure to run this uh but also at the same time maintaining it you could just use any cloud. They do charge a monthly pricing but at the same time you do get a lot more convenience if you're just starting out with automating things through an end and you don't need to spend a lot of time worrying about all the other stuff in terms of

maintenance of the infrastructure. So let me know what you guys think and what you guys prefer. Otherwise I'll see you in the next section. Congratulations, you made it to the end of the course. Think back where we started at the beginning of this course. Notes and sub workflows may have felt abstract. Now you've not only learned the fundamentals, you've actually built intelligent productionready workflows from scratch. That's a huge step. Along the way, you've explored how to connect

APIs and services with HTTP request node and build AI powered agents that automate real world tasks like email replies, research, and even select conversations on your behalf. You've also learned how to generate images and videos directly from text or media inputs and also use sub workflows to organize complex systems into reusable modular components. And you've also learned how to host NDN anywhere from edit at cloud to docker or AWS EC2 giving you the flexibility of your own

environment. We then move into a non territory rag agents with pine cone back to databases enabling memory and contacts in your automations. You've also learned how to use MCPS in your NDN workflows to scale and reuse some of the building blocks. And of course, we've gone through the best practices in terms of error handling, retries, and leveraging the end template marketplace to accelerate your builds. By now, you've seen how automation goes beyond just saving time. It's about

orchestrating systems, extending the reach of AI, and freeing yourself from repetitive work so you can focus on higher value tasks. So, where do we go from here? First, get building. The workflows we've covered are a strong foundation, but end is also limitless in its flexibility. Try connecting new APIs, experiment with custom nodes, and layer in new additional agents. The more you explore, the more powerful your automations become. Second, share and learn with others. At CodeCloud, you're

part of a global community of learners, engineers, and automation enthusiasts. Ask questions, showcase your workflows, and draw inspiration from others projects. Collaboration is one of the best ways to grow your skills. And if you like to share feedback, ideas, or just to show me some of the cool stuff that you built, feel free to get in touch with me. I'd love to hear what you build with ended. Third, think about your own environment. Could you integrate end into your DevOps

pipelines, replace manual reporting with AIdriven summaries, or deploy customer support agents that scale your businesses? Whatever your role is, automation is a lever that you can pull to create real impact. A final thought, remember automation isn't about replacing people. It's about augmenting what you do. By letting Editen handle the repetitive, the mechanical, and the time-conuming, you create more space for creativity, strategy, and innovation. So, keep experimenting and keep building

and keep pushing boundaries on what's possible with Na. Thank you for lending with me and with Docloud. I'm Maronei and I can't wait to see what you build with that event.

So I want to run through the differences between running your instance on end cloud versus the lab playgrounds that we have on the code cloud course. Now the first thing you'll notice as you go into the lab is that you still have to provide your email and your first name, last name credentials as well as a password in the instance. And don't worry, this is not saved anywhere. So you don't actually have to save the credential and the password somewhere. You can use different emails and

password for each of these instances. So once that's filled in, you can hit next. And there's going to be a series of onboarding questions here which you don't need to fill. So you can hit get started. And in the same way for the paid features information, you can just skip. And there you go. And now you're in the admin dashboard that is very similar to the N9 cloud environment. However, there's still some nuances and some differences as we go into the workflow. So here what we're going to do

is we're going to click start from scratch. And the very first workflow that you're going to build is the email AI agent. And the first trigger to that is a chat trigger. And I'm going to speed through this because this is very similar to the workflow that we've done. But I want to just show you quickly the differences of using the codecloud keyspace as well as the open AI API key. So if you're using the codecloud keyspace, what you want to do when you select your model, for example, in this

case, I'm just going to select the open AI chat model. And what I want to do is to follow the instruction in the left hand bar right here. And you see that there's a link to code key. I'm going to just hit that URL. And I'm going to hit launch now. and it's going to lead me to this dashboard right here. I'm going to click start playground and there we go. So, this is the dashboard on CodeCloud Keyspace. And what I want to pick is the OpenAI GPT 4.1. And in this case, I'm

going to just copy the API key here. I'm going to go back to my workflow. And here, I'm going to hit create credential and I'm going to paste the same exact API key. I'm going to skip the organization ID. And for the base URL, I want to make sure that I'm replacing this with the base URL that I obtained from the CL keyspace. Go back to my lab and paste the base URL right here. Okay, so I'm going to hit save right now. As you can see, it says connection tested

successfully. However, there's a couple of things I want to point out here. Cuz if you pick from list, as you can see, the list doesn't really match the known models of GPT. This is because it's not really working based on the UI that's been built. So if you try to run it based on the chat ID or chat model that we've selected, I'm just going to run a hello message here. It's going to go to the AI agent, but it's going to error out. So what you need to do is go into

the chat model and instead of picking from list, you want to go by ID and as suggested from the instruction on the left hand bar here, you want to copy the OpenAI/GPT-4.1. Just copy that and paste it all word for word. And let's do a test run again. And this time it should actually be able to access the appropriate model. So that's if you're using the CodeCloud keyspace API keys. Now what I want to point out is the difference between this and using the OpenAI API key is that it's much

more straightforward when you use OpenAI API keys. So to show you the difference, what I'm going to do here is I'm going to create another new credential and I'm going to call it OpenAI account too. This time I'm going to head over to platform.openai.com. And what I want to do is head over to API key section. I'm going to create a new secret key in and then email integration. I'm going to hit create secret key and I'm going to copy the API key and head back to my lab. I'm going

to paste the API key and leave the base URL as is and I'm going to hit save. So there you go. So connection tested successfully. And the difference is instead of by ID, I can now just pick from the list and it should load up the correct list of models that I might possibly want to use. So for example, if I choose GPT 4.1, it's just going to be that. And we're going to run this node again. And as you can see, it's calling the correct model right here. Okay. So

the next thing I want to point out is when you add your Gmail note on the next workflow or Google tool for that matter the difference between doing that in our labs versus edit cloud is that on edit cloud you often see when you create a new credential with Gmail that you can actually have a button which you can sign in directly using your Google account if your browser happens to be a Google Chrome browser. However with the labs what you need to do when you create

a new credential is you actually need to connect it with the oorthth method. So what you want to do is you want to head over to console.cloud cloud.google.com. And the first thing you want to do is create a new project. And for the new project, I'm going to name it in email app. All right. So, I'm going to leave this as no organization. I'm going to hit create. And it's going to take a couple seconds to create the project. And once that's done, I'm going to

select the project. And as you can see, it says edit an email app project. And the very first thing I want to activate is I want to go to Gmail API. So what I'm doing right now is I'm creating a project because that's how Google recognizes each of these oath access that we're giving it. But the way the security works is you need to enable the particular tool that you want to use within the project. So in this case I want to use Gmail. So I want to make sure I enable the Gmail API. All right.

Once that's enabled, I want to head over to OOTH consent screen. And right now there's no OOTH consent that's set up. So I'm going to just hit get started. And in this case, I'm going to have to call it an app name as well. So I'm just going to say it is an email app. Okay. User support email. Going to put this. And we're going to select external. And by the way, each of these steps is documented on the left hand side panel of the lab. So you don't have to memorize any of these. But we're going

to go to next. And under contact information, just going to put my email here. And once you're done, just hit continue. and create. So, just before we go, I just want to go to audience and I want to add a test user here, which is an email that you're going to use to send out basically the emails that you want the agent to send out. So, in this case, it's maronei atcloud.com. We're going to save that. And lastly, we're almost there. We're going to go to API and services again, and this time we're

going to go to credentials. And what we want to do is to hit create credentials with OOTH client ID. And application type we want to choose web application. And under name you want to name it Canadian email oath client. And then we're going to add the authorized redirect URLs which we can obtain from our lab. So going back into the lab here, you see that this is the OOTH redirect URL. and we're going to copy this and we're going to head back and just fill this in and we're going to hit

create. As you can see, we now have the client ID and client secret to the app that we just created. So, we're going to copy this and head back to client ID. Paste it in. Client secret. Copy that. Paste in the client secret. And you'll see now that there is a sign in with Google button that pops up. So, what you want to do is just hit that and a Google login pop-up will show. And then you just want to correctly select the email address. And you'll say that Google

hasn't verified this app. But because you're the one who created it, you know it's safe. So we're just going to hit continue. And we're going to select all because we want to have the agent be able to do all these actions with our Gmail. So we're going to hit continue now. And as you can see, it says connection successful. And we're good to go. So just wait a couple seconds here within the labs and it's just going to load up. And there you go. I already have my credential set up here. And we

just want to run an execute step to show you that everything is working. So in the workflow, you'll see that we've chosen to define all of this by the model. So we're going to let the AI agent define this. And we're going to start chatting and say, "Hi, can you send an email to codingcloud.com to just say hello?" All right. So we're going to hit this. So as you can see now the workflow has run and it's actually sent an email to my Gmail. So let me take a look. And there you go. It says

hello mer just want to say hello best regards. Okay. So obviously it's not very sophisticated because actually in the AI agent we didn't even specify any system prompt. So the whole point is just to show you the main difference between running the environment on end cloud and within our playgrounds specifically covering the part where code key is being used as well as when you're going to access any Google tools Gmail, Google Sheets and stuff like that. You do need to go to your Google

cloud console to set up the project, the app, and the ooth clients in order to access Google services with the workflow. And as you explore Nit in the course, you're going to realize that there's going to be some differences between running edit cloud and edit within your own self-hosted environment. For example, the availability of community notes, supported versions, and a few other features that might only be available on edit cloud. So if you're facing any issues any part of that

build, just keep in mind that it might be because you're using a self-hosted version or a lab hosted version from CodeCloud. And it's not necessarily a limiting issue. There's always a workaround for that. It's just something to keep in mind about