DDrona4U
Sign inCreate account
My learningAGENTIC AILesson 15
Agentic RAG: AI Agents That Decide What to Retrieve and When

Lesson 15

Agentic RAG: AI Agents That Decide What to Retrieve and When

Agentic RAG extends traditional RAG by allowing the AI agent to intelligently decide what information to retrieve, when to retrieve it, and how many retrieval steps are needed to complete a task effectively.

Get the full lesson

Sign in to unlock everything beyond the preview — it's free.

  • Take timestamped notes as you watch
  • Read the full transcript and download resources
  • Join the discussion and track your progress
Sign inCreate free account

Curriculum

21 lessons · 1h 24m

0/21 lessons done1h 24m left
  1. 0104:15

    Why an AI Agent Is More Than a Chatbot

    04:15

  2. 0203:57

    LLM Brain vs Agent Body

    03:57

  3. 0304:14

    AI Autonomy Levels: Copilot to Fully Autonomous Agent

    04:14

  4. 0404:27

    The AI Agent Loop: Observe, Think, Act, Reflect

    04:27

  5. 0503:38

    When to Use AI Agents vs When They’re Overkill

    03:38

  6. 0603:53

    ReAct: The Reason-and-Act Framework Behind Modern AI Agents

    03:53

  7. 0704:14

    Tool Calling: How an LLM Chooses the Right Action

    04:14

  8. 0804:01

    Function Schemas: Teaching AI Models What Tools They Can Use

    04:01

  9. 0904:00

    AI Planning: Breaking Big Goals Into Actionable Steps

    04:00

  10. 1003:53

    AI Reflection: Self-Checking Before Responding

    03:53

  11. 1103:47

    Chain-of-Thought vs Scratchpad Reasoning in AI Agents

    03:47

  12. 1203:40

    Context Window: An AI Agent’s Working Memory & the Lost-in-the-Middle Problem

    03:40

  13. 1303:54

    Short-Term vs Long-Term Memory in AI Agents

    03:54

  14. 1403:45

    RAG: Giving AI Agents Knowledge Without Retraining the Model

    03:45

  15. 03:33

    Agentic RAG: AI Agents That Decide What to Retrieve and When

    03:33

  16. 1603:46

    Agent State: The Memory Layer Behind Production-Ready AI Agents

    03:46

  17. 1704:04

    MCP: The Universal Connector for AI Tools and Agents

    04:04

  18. 1803:30

    Why MCP at the Linux Foundation Reshaped AI Frameworks in 2026

    03:30

  19. 1903:49

    Structured Outputs: When AI Must Return JSON Instead of Text

    03:49

  20. 2004:40

    AI Sandboxes: Safe Environments for Agents to Run Code and Tasks

    04:40

  21. 2104:47

    Computer-Use Agents: AI That Operates Software Like a Human

    04:47