Mar 23
Loading video player...
Sponsored by Scalekit (OAuth + Tool Execution for AI Agents) → https://tinyurl.com/5h9vssuv LangChain. LangGraph. LangSmith. If you’ve been exploring AI agents, you’ve definitely seen these names. But what do they actually do, and why do you need all three? In this video, we break down the complete AI agent stack, from simple LLM calls to production-grade systems with reasoning, tools, and observability. You’ll learn: • Why raw LLM APIs are not enough • How LangChain structures prompts, chains, tools, and RAG • What AI agents are and how the ReAct loop works • Why LangGraph is needed for stateful workflows and control flow • How LangSmith helps debug, evaluate, and monitor AI systems • How all three fit together into a real-world architecture This is a ground-up system design explanation for engineers building real AI products. Resources: - System Design Course: https://academy.bytemonk.io/courses - ByteMonk Blog: https://blog.bytemonk.io/ - LinkedIn: https://www.linkedin.com/in/bytemonk/ - Github: https://github.com/bytemonk-academy Timestamps 0:00 – The AI Stack Everyone Talks About 0:45 – Why Raw LLM APIs Are Not Enough 1:38 – LangChain: Prompts, Chains, Tools & RAG 4:50 – The Real Challenge: Tool Access & OAuth using Scalekit 6:12– What Are AI Agents? (ReAct Loop Explained) 7:00 – LangGraph: Handling State, Loops & Control Flow 8:55 – LangSmith: Debugging & Observability 10:08 – How the Full Stack Fits Together + Honest Take https://www.youtube.com/playlist?list=PLJq-63ZRPdBt423WbyAD1YZO0Ljo1pzvY https://www.youtube.com/playlist?list=PLJq-63ZRPdBssWTtcUlbngD_O5HaxXu6k https://www.youtube.com/playlist?list=PLJq-63ZRPdBu38EjXRXzyPat3sYMHbIWU https://www.youtube.com/playlist?list=PLJq-63ZRPdBuo5zjv9bPNLIks4tfd0Pui https://www.youtube.com/playlist?list=PLJq-63ZRPdBsPWE24vdpmgeRFMRQyjvvj https://www.youtube.com/playlist?list=PLJq-63ZRPdBslxJd-ZT12BNBDqGZgFo58 #LangChain #aiarchitecture #bytemonk