Lesson 3 of 5

Tools and Agents

Give the model the ability to act, then let it decide its own steps, and see what that costs.

Lesson 3: Tools and Agents
Chapters · 10 0:00 Welcome
The production AI system you build in the Engineer's AI Accelerator
Flagship course

Want to build production-grade agentic systems?

The Engineer's AI Accelerator has you build one on your own data: agentic retrieval, evaluation, security and observability, all the way to deployment.

  • Every layer of a production AI system, from ingestion to agents and deployment
  • A decision framework for every layer
  • Every choice backed by experiments and evals
  • Graded milestones, plus a 24/7 AI TA
See the Accelerator

Taken by 100+ engineers from Microsoft, Amazon, Apple and more.

By the end of this lesson

  • You'll understand how tool use works, and where MCP fits
  • You'll see what changes when a review runs on measured facts instead of estimates
  • You'll know what actually makes a system an agent, and what that autonomy costs
  • You'll see why a system that looks right still isn't proven

How was Lesson 3?

I'd really love to know how this lesson landed for you. Whatever you share, the good and the not-so-good, helps shape what I make next.

1. Overall, how would you rate this lesson? (required)
2. How was the pace?
Can we share your feedback?