Sign in Explore the program

Unlocks after Module 9The AI Engineering Program

Module 10: Agents & MCP

Build agents that use tools, remember context, ask a human before risky steps, and plug into real software through MCP.

32guided hours
13lessons
10 of 13in the program
Enrol in the programTry lesson 1 free

Lessons

13 lessons, in order. Each one unlocks when you finish the one before it.

  1. 10.1
    Workflows vs agents: choosing the simplest thing that works
  2. 10.2
    The tool-use loop, built without a framework
  3. 10.3
    Planning, reflection and routing patterns
  4. 10.4
    LangGraph: state, nodes and checkpoints
  5. 10.5
    Agent memory: short-term and long-term
  6. 10.6
    Building an MCP server
  7. 10.7
    MCP clients: connecting agents to spreadsheets, GitHub and databases
  8. 10.8
    Multi-agent orchestration
  9. 10.9
    Human-in-the-loop approvals
  10. 10.10
    Evaluating agents and controlling their cost
  11. 10.11
    Voice agents, including Indian languages
  12. 10.12
    Browser and computer-use agents: capabilities and safety
  13. 10.13
    Module project
PreviousModule 9: Evals, Guardrails & AI SecurityNextModule 11: Fine-Tuning, Open Models & Inference

See all 13 modules

Your first lesson is on us.

AI vs ML vs DL vs GenAI: deep notes, a hands-on lab and a quiz. No card. No catch.

Start lesson 1 free