Overview
Ivan Leo from Manus AI (now Meta Superintelligence) demonstrates building intelligent research agents using the Manus platform and API. The core insight is that building a general AI agent first, rather than verticalized products, enables far more versatile applications - from language learning apps to conference event scrapers to Slack bots that can handle complex multi-step workflows.
Key Takeaways
- Design general agents before specialized products - Manus built a general AI agent that can be deployed across web, Slack, mobile, and API, rather than creating separate tools for each use case
- Leverage authenticated browser access for real workflows - The remote browser operator can use your logged-in accounts (LinkedIn, Instagram, etc.) that sandboxed browsers can’t access, enabling automation of personal workflows
- Context management scales automatically - With unlimited context management and smart KV caching, you can build complex multi-turn conversations without worrying about token limits
- File uploads auto-delete for security - All files uploaded via the API are automatically deleted after 48 hours unless explicitly removed earlier, solving the sensitive data retention problem
- Multi-platform consistency reduces integration complexity - API billing matches web app usage exactly, so you can choose deployment method based on user needs rather than cost considerations
Topics Covered
- 0:00 - Introduction and Manus Overview: Workshop introduction, explaining what Manus is and the philosophy of building general AI agents that meet users where they are
- 3:00 - French Learning App Demo: Demo of a personal French learning application built with Manus that provides inline corrections, explanations, and voice synthesis
- 6:30 - Remote Browser Operator Demo: Demonstration of the browser operator finding coffee shops using authenticated Google Maps access on the user’s actual browser
- 9:00 - Conference Event Scraper: Building a custom website that scraped all AI Engineer conference events, created embeddings for similarity search, and generated personalized timelines
- 12:30 - Manus API Fundamentals: Core API concepts including authentication, task creation, polling vs webhooks, and asynchronous lifecycle management
- 23:00 - File Upload and Context Management: Three methods for providing context: file uploads, public URLs, and base64 encoded images, with automatic cleanup and multimodal support
- 31:00 - Webhooks for Scale: Implementing webhooks using Modal for production-ready task completion notifications instead of polling
- 37:00 - Slack Bot Integration: Building a complete Slack bot that handles multi-turn conversations, file uploads, and threaded responses with proper state management
- 1:08:00 - Invoice Processing Demo: Advanced demo showing OCR receipt processing integrated with Notion company policies for automated expense reporting
- 1:13:00 - Q&A and Use Cases: Audience questions about data privacy, memory features, browser integration, and interesting real-world use cases like automated pickle ball court booking