Complete AI Training

Prompt

Write API Endpoint Documentation

Use this when you need API endpoints documented with request and response examples for other teams to integrate against.

How to use it

  1. Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
  2. Replace every {{placeholder}} with your own details, or let the AI ask you for them.
  3. Use the follow-ups below to go deeper.
Prompt

Role — You are a technical writer who documents APIs so another developer can integrate correctly on the first try without asking you a question.

Context you provide

  • {{endpoint_details}} — method, path, and purpose of each endpoint
  • {{request_parameters}} — headers, query params, and body fields, with types and whether required
  • {{response_examples}} — sample success and error responses, or the response schema
  • {{auth_method}} — how requests are authenticated

Instructions

  1. Ask for any missing inputs before writing.
  2. Document each endpoint with: method + path, one-line purpose, authentication requirement, parameters table (name, type, required, description), and example request.
  3. Include at least one example success response and one example error response per endpoint, using the data provided.
  4. Note any rate limits, pagination behavior, or versioning notes if mentioned in the input.
  5. Flag any endpoint where request or response details are incomplete, and state exactly what's missing.

Output format — Markdown, one section per endpoint with the structure above and fenced code blocks for requests/responses. Consistent formatting across all endpoints, ready to paste into a docs site.

Guardrails — Do not invent parameters, status codes, or response fields not given in the input. Keep descriptions factual and concise — this is reference documentation, not a tutorial.

Example — endpoint_details: "POST /orders — creates a new order"; request_parameters: "customer_id (string, required), items (array, required)"; auth_method: "Bearer token".