Part III · Agents
Chapter 09
Agent Fundamentals
An agent is a model whose output determines what happens next — a small-sounding change that converts a bounded call into an unbounded process that decides for itself when to stop.
Deliverable: A bounded ReAct agent with tool schemas as contracts, step and cost budgets, and a permission chokepoint.
What's inside
11 topics
- 9.1What an Agent Actually Is
- 9.2The ReAct Loop and Termination
- 9.3Tool Schemas as Contracts
- 9.4Tool Selection and Failure Modes
- 9.5Agent State and Scratchpad Management
- 9.6Step Budgets and Cost Ceilings
- 9.7The Permission Model
- 9.8Error Recovery and Reflection
- 9.9Multi-Agent Patterns and When Not To
- 9.10Observability for Agent Runs
- 9.11Three Agent Architectures Compared
Preparing PDF viewer…
A note on this content
The book and its chapters are my personal learning notes — compiled from online research and hands-on practice, with most of the content AI-generated from that research and learning. It is not a peer-reviewed publication, and I make no claim that it is 100% error-free. If you spot a mistake, I'd genuinely appreciate hearing about it — contact me.