Jan 16
Loading video player...
AI agents are no longer confined to chat interfaces. From our original Manus app for powerful conversations, to Mail Manus for transforming your inbox into an organized command center, we've progressively expanded where an AI can work. Now, with the Manus API, we're completing the vision by giving you the final building block to deploy an intelligent agent anywhere in your stack. In this workshop, you'll learn to use the API to build a bespoke research agent that powers deep analysis across your company's internal data. We'll show you how to dispatch a task that connects to your private systems, synthesises complex information, and delivers custom insights on demand, turning your entire knowledge base into an actionable, intelligent asset. In this hands-on session, you will: - Use the Manus API to dispatch and manage asynchronous agentic tasks. - Connect the agent to private data sources using our connectors - Build a complete workflow that synthesises information into a custom report. By the end of the workshop you'll have a functional research agent that you can adapt for your own use case. ## SUMMARY Ivan introduces **Manus 1.5** and the new **Manus API**, positioning Manus not just as a chatbot but as a "general action engine" capable of executing complex workflows, automating tasks, and extending human reach. Ivan Leo demonstrates the ecosystem—including a web app, Slack integration, browser operator, and Microsoft 365 integration—before diving into a workshop on building bespoke research agents. The session concludes with a Q&A covering advanced use cases like Python scripting for booking slots, browser security permissions, and future roadmap features like memory retention and document exporting. **Timestamps:** 00:00 Introduction & Workshop Overview 00:53 What is Manus? (The Action Engine) 01:18 Manus 1.5 Updates (Performance, Quality, Architecture) 02:23 Manus Ecosystem (Web, Slack, API, Browser, M365) 03:15 Demo: French Learning App (Custom Web App) 06:02 Demo: Mail Manus (Email Automation) 06:51 Demo: Browser Operator (Coffee Search) 01:18:00 Use Case: Pickleball Booking Script 01:18:44 API & Browser Permissions 01:19:21 Future Features: Exporting to PPTX/PDF 01:20:05 Memory & Context Management