Lesson 9 — ReAct Loop

This lesson implements Reason+Act (ReAct): an agent alternates thoughts with tool calls until it answers or hits a step limit. Unlike one-shot prompting, every thought, action, and observation is visible for debugging. Three tools — search, calculate, lookup — sit behind a planner in react/loop.py; MetricsStore records each step; a FastAPI dashboard shows live counters. POST /demo runs three questions so metrics move from zero after the first click.

The project in aiam-day09/ runs via start.sh, demo.sh, and run_tests.sh.

• Thought → Action → Observation with stopping on final_answer or max_steps.

• Tool dispatch via Action: name[argument] parsed by strict regex.

• AST-safe calculator — no eval().

• Dashboard polls /metrics; /demo exercises all three tools.

• Docker lifecycle scripts on port 8088.

• react/ package: tools.py, loop.py, metrics.py, service.py.

• FastAPI (app.py): /run, /demo, /metrics, /health, /dashboard.

• CLI demo (main.py) printing steps, observations, and final answers.

• DEMO_QUESTIONS — search, calculate, lookup — so every dashboard counter updates.

Day 8 fanned typed work to workers in parallel. Day 9 sequences one tool per step: observe, then continue or stop with a Final Answer.

ReAct is the control loop prompt engineering will steer. Production swaps _plan_thought() for an LLM; the action/observation contract and metrics stay the same.

• Where this component sits: between app.py (API) and react/tools.py (tool backends).

• Why it exists: multi-step questions need grounded facts before a final answer.

• Problem solved: bounded, observable tool use with measurable loop health.

Continue reading this post for free, courtesy of AI Roadmap.