Chapter · AI

Agents & Tool Use

What changes when a model can call functions, browse the web, run code, and chain decisions across hundreds of turns. The patterns, the harnesses, and the failure modes.

Topics
Topic 1

Agent Fundamentals

The loop that turns a stateless model into something that acts in the world.

Planned
Topic 2

Tool Calling

How the model asks for external functions, and how their results flow back into context.

Planned
Topic 3

Harness Engineering

The scaffolding that decides what the agent sees, can do, and remembers.

Planned
Topic 4

Multi-Agent Systems

When one model isn't enough — coordination, debate, delegation, and where each pattern earns its keep.

Planned
Topic 5

Long-Horizon Tasks

Keeping an agent on track across hundreds or thousands of steps without drifting.

Planned
Topic 6

ReAct, Reflection & Planning Patterns

The canonical control flows agent frameworks expose, and when each is the right choice.

Planned
Topic 7

Coding Agents

The most successful agent application — and the techniques that got it there.

Planned