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.
Agent Fundamentals
The loop that turns a stateless model into something that acts in the world.
Tool Calling
How the model asks for external functions, and how their results flow back into context.
Harness Engineering
The scaffolding that decides what the agent sees, can do, and remembers.
Multi-Agent Systems
When one model isn't enough — coordination, debate, delegation, and where each pattern earns its keep.
Long-Horizon Tasks
Keeping an agent on track across hundreds or thousands of steps without drifting.
ReAct, Reflection & Planning Patterns
The canonical control flows agent frameworks expose, and when each is the right choice.
Coding Agents
The most successful agent application — and the techniques that got it there.