Your build starts here
Replace bracketed details with your own goal, context, and checks. Keep the first build small enough to inspect.
Investigate this server failure: [exact symptom]. Reproduction: [method, route, sanitized input, and actions]. Expected result: [result]. Observed response: [status and sanitized body].
Follow one request through parsing, authentication, authorization, business logic, and storage. Use a request identifier or other relevant evidence to correlate logs. Separate a code failure from missing configuration or an unavailable dependency.
Test the explanation that best fits the evidence, apply a focused correction, and repeat the original request. Check a relevant neighboring case. Report the cause, changed files, actual storage result, and verification limits without exposing credentials.Make this prompt yours
Replace bracketed fields with your goal, current behavior, and relevant evidence. Keep requirements that affect the task. Check the result against the acceptance criteria you supplied.
The docs behind it
These references explain the underlying concepts and APIs. The prompt templates and project plans are original examples to adapt to your own setup.
Documentation links checked .
Editorial review · October 28, 2026
Supported: Original, unexecuted diagnosis template. Middleware and request tracing are technically grounded; it asks for evidence instead of inventing the failing component.