Building Intelligent Research Agents with Manus
summary
Demos show the Manus API creating asynchronous agent tasks that query private connectors, upload large files, and return structured reports with task IDs and URLs; uploads come with files auto-delete in 48 hours and public-URL ingestion is supported. Live examples include scraping conference pages into a searchable site, parsing PDFs and receipts into Notion, and automating bookings with Python/Selenium via a remote browser operator. Webhooks, Slack integration, KV thread mapping, and planned features like memory and PPTX/PDF export are covered end to end.
AI-written summary · about
chapters (11)
- 0:00Introduction & Workshop Overview
- 0:53What is Manus? (The Action Engine)
- 1:18Manus 1.5 Updates (Performance, Quality, Architecture)
- 2:23Manus Ecosystem (Web, Slack, API, Browser, M365)
- 3:15Demo: French Learning App (Custom Web App)
- 6:02Demo: Mail Manus (Email Automation)
- 6:51Demo: Browser Operator (Coffee Search)
- 1:18:00Use Case: Pickleball Booking Script
- 1:18:44API & Browser Permissions
- 1:19:21Future Features: Exporting to PPTX/PDF
- 1:20:05Memory & Context Management
related talks
40mAI Agents in Practice
30mBuilding Robust, Secure LLM and Agentic AI Workflows
49mAI Agents: Collaboration in Real-Life Applications
01h 23mA2A & MCP Workshop: Automating Business Processes with LLMs
21mBuilding Agents (the hard parts!)
18mBuilding AI Agents that actually automate Knowledge Work
02h 08mIntroduction to AI Agents
01h 57mFull Workshop: Build Your Own Deep Research Agents