Build AI Agents That Work While You Sleep | Deep Agents

Video Description

LLM Agents tackle longer and more complex task with deep agent frameworks! Resources: Notebook and Agent Code - https://github.com/ALucek/deep-agents-walkthrough LangChain Deep Agents - https://github.com/langchain-ai/deepagents LangChain Deep Agents UI - https://github.com/langchain-ai/deep-agents-ui Agent System Prompt Repo - https://github.com/x1xhlol/system-prompts-and-models-of-ai-tools LangChain Deep Agents Blog - https://blog.langchain.com/deep-agents/ Manus Context Engineering Blog - https://manus.im/blog/Context-Engineering-for-AI-Agents-Lessons-from-Building-Manus METR Measuring AI Ability to Complete Tasks - https://metr.org/blog/2025-03-19-measuring-ai-ability-to-complete-long-tasks Claude Code Todo List - https://claudelog.com/faqs/what-is-todo-list-in-claude-code/ Claude Code Sub Agents - https://docs.claude.com/en/docs/claude-code/sub-agents HCAST: Human-Calibrated Autonomy Software Tasks - https://metr.org/hcast.pdf Claude 3 Opus as an economic Analyst - https://www.youtube.com/watch?v=sjL6Gl6ZIqs Chapters: 00:00 - What Are Deep Agents? 03:50 - Overview: System Prompts 11:04 - Overview: Planning Tool 13:50 - Overview: File System 16:15 - Overview: Sub Agents 20:17 - Build: Setup & Idea 22:15 - Build: Prompting 27:40 - Build: Compiling The Deep Agent 29:07 - Build: Deploying 30:15 - Build: Running the Deep Agent 30:52 - Build: Reviewing the Trace 34:46 - Build: Reviewing the Output 36:08 - Build: Statistics & Takeaways #ai #programming #datascience