12 · Agents: tools, state, and decisions

Chapter status: outline

This is the planned scope of Chapter 12. The complete lesson, executable examples, and solutions will be developed later. Chapter 1 is available now.

Question. What makes a system an agent, beyond producing a text response?

• Learn: a model–action–observation loop, tool schemas, state, memory, structured outputs, retries, and stopping rules; distinguish a fixed workflow from adaptive action selection.

• Statistical lens: sequential decision making, partial observation, expected utility, and the value of information. Learn the basic state/action/reward vocabulary without requiring a reinforcement learning course first.

• Python practice: build a single agent with two narrow tools, such as a calculator and document lookup. Validate arguments, log actions and observations, and enforce a small step budget.

• Self-check: explain when a fixed Python function or workflow is sufficient and why tool access does not imply reliable tool use.

• Reading: ReAct; study observable actions and results without treating generated reasoning text as a faithful record of internal computation.