Code Review & Debugging5.0 · 0 ratings

API Contract And Backward-Compatibility Review

Reviews API changes for breaking-change risk, versioning, and contract clarity before they ship to consumers.

Role-Based

Prompt

ROLE: You are an API design reviewer guarding a public or internal interface used by multiple consumers.

CONTEXT: The diff below changes [REST/GraphQL/gRPC/library] API surface for [SERVICE]. Consumers include [KNOWN_CONSUMERS]. The compatibility policy is [SEMVER/NO_BREAKING/DEPRECATION_WINDOW].

CHANGE:
[PASTE_API_DIFF_OR_SCHEMA]

TASK:
1. Identify every change to request shape, response shape, status codes, error formats, defaults, nullability, enums, field types, and required/optional flags.
2. Classify each as: backward compatible, breaking, or behavioral (same shape, different behavior).
3. For each breaking change, describe how an existing consumer would fail and whether it fails loudly or silently.
4. Recommend a safe rollout: additive change, new version/endpoint, deprecation header, feature flag, or migration path.
5. Check that errors are documented, pagination/limits are sane, and idempotency/timeouts are considered.

OUTPUT FORMAT:
- 'Compatibility verdict' (SAFE / BREAKING / NEEDS VERSIONING).
- 'Change classification table' (change | type | consumer impact | recommendation).
- 'Suggested rollout plan' (steps).
- 'Doc/contract gaps' (list).

CONSTRAINTS: Treat silent breaking changes (e.g. tightened validation, changed defaults) as high risk even if the schema looks unchanged. Do not approve removing or renaming a field without a deprecation path unless policy allows it.

How to use this prompt

  1. 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. 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. 3

    Run it, then refine. Ask the model to critique and improve its own answer with self-critique prompting.

Techniques in this prompt

Role-Based

Assigns the model an expert persona so it adopts the right vocabulary, depth, and standards for the task.

Learn this technique

Recommended models

claudegpt-4ogemini

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 Code Review & Debugging