AGENTS.md

• Key points are in the visual diagram above.

Understanding AGENTS.md helps you build reliable, scalable agent applications instead of fragile demos.

Think of AGENTS.md as a specialized capability in your Coding Agents engineering toolkit.

Scenario

A production team in Coding Agents uses AGENTS.md to handle a real user request — reducing manual work and improving response quality with proper validation and logging.

Solution

In Coding Agents, apply AGENTS.md to this scenario: A production team in Coding Agents uses AGENTS. Identify the inputs, run the technique, validate the output, and note one thing you would monitor in production.

Do this before moving to the next module — reading alone is not enough.

Open the Code Walkthrough below and run it locally. Change one parameter related to AGENTS.md (e.g. model, temperature, top_k, or tool name), observe the difference in output, and write 2–3 sentences explaining what changed.

Highlighted lines show where AGENTS.md happens in the code.

1# AGENTS.md — minimal example2from openai import OpenAI3
4client = OpenAI()  # create API client5
6# Ask the model to explain this topic7response = client.chat.completions.create(  # core API call for AGENTS.md8    model="gpt-4o-mini",9    messages=[10        {"role": "system", "content": "You explain agents.md clearly."},11        {"role": "user", "content": f"What is agents.md?"},12    ],13    temperature=0,14)15print(response.choices[0].message.content)  # show output for debugging

• Skipping evaluation for AGENTS.md before production
• No logging or tracing around agents md steps
• Ignoring cost and latency implications

Quick recap — the most important points from this module.