Bug Repro — Minimal Failing Case
Turn a vague bug report into a clean repro: steps, expected vs actual, environment.
Prompt
**Role:** Senior support engineer who has filed 1000+ bug reports to engineering teams. You know that the difference between a fixed bug and a closed-as-can't-repro bug is the quality of the first 60 seconds of reading. **Context:** A user reported: "[the vague bug report]". They're using [product version] on [OS/browser]. Their description includes some hand-waving and some specifics. **Task:** Convert the report into a minimal reproducible test case that an engineer can run in under 90 seconds and either reproduce or definitively rule out. 1. Title: imperative + specific. Not "Login broken" but "Login fails with HTTP 500 when email contains '+' character on iOS Safari 17." 2. Environment: product version, OS, browser, locale, account type, anything else relevant. 3. Steps to reproduce: numbered, exact, copy-pasteable URLs and inputs. 4. Expected behavior: what the user expected to see, in one sentence. 5. Actual behavior: what they saw — quote any error message verbatim. 6. Minimal repro: the smallest possible variation. Strip away every confounding variable. 7. Workaround (if any): what the user is doing now to get unblocked. **Constraints:** - Quote error messages exactly — never paraphrase - Include console errors, network 4xx/5xx, and any user-visible state - If you can't repro on your machine, say so — list what you tried - No speculation about cause unless you have evidence **Output format:** GitHub issue template · 7 sections · screenshots/HAR file references in [brackets].
How to use this prompt
- 1
Copy the prompt above and paste it into ChatGPT, Claude, or Gemini — or open it in the visual Studio to edit each part on a canvas and run it with your own key.
- 2
Replace any bracketed placeholders with your specifics. The more concrete your context and constraints, the sharper the result — see the 5-part prompt structure.
- 3
Run it, then refine. Ask the model to critique and improve its own answer with self-critique prompting.
Techniques in this prompt
Assigns the model an expert persona so it adopts the right vocabulary, depth, and standards for the task.
Learn this techniqueSpecifies the exact shape of the result — sections, a table, JSON, a word count — so the output is predictable and ready to use.
Learn this techniqueSets the rules and boundaries — tone, length, what to avoid — that keep the output on-target.
Learn this techniqueRecommended models
Build on this prompt
Open it in the visual Studio to wire it into a full workflow with your own API key — or learn the craft behind prompts like this.
More in Engineering
Staff-Engineer Code Review
Reviews a PR like a senior who optimizes for the next reader, not style nits.
Architecture Decision Record (ADR)
Write an ADR that future-you will still understand in 18 months.
Blameless Postmortem
Outage report that reduces fear of speaking up and produces real action items.
Tech Debt Prioritization
Rank a backlog by leverage × pain × confidence. Output an ordered ranking.