Intermediate About 120 minutes 5 stages

Review an AI-assisted code change before release

Move an AI-assisted code change from a clear requirement through security, testing and accountable human approval.

Review an AI-assisted code change before release

What you will produce

A reviewable result, not an automatic answer.

Follow the stages in order. Each stage ends with a tangible deliverable and a review checkpoint, so mistakes are caught before they become the next tool’s input.

Expected tool cost

Use free plans where suitable; confirm current provider limits and prices before starting. Compare the latest verified AI pricing before buying another subscription.

Suggested stack

Tools used in this workflow.

The process matters more than the brand. Use an approved equivalent when it offers the controls and output quality your organisation needs.

Inputs and ownership

Before you start

  • A version-controlled codebase, issue and acceptance criteria
  • A safe development environment without production secrets
  • An authorised reviewer who understands the affected system

Interactive workflow

Complete each stage in order.

Tick a stage only after its deliverable and review checkpoint are complete.

  1. Translate the requirement into acceptance criteria, affected components, constraints and a rollback expectation.

    Deliverable

    A reviewable engineering brief

    Review checkpoint

    Never expose credentials, customer data or production configuration.

  2. Ask the assistant to inspect relevant code and propose a small change plan before generating code.

    Deliverable

    A bounded implementation plan

    Review checkpoint

    Inspect every changed line and dependency.

  3. Implement the smallest coherent change with comments only where they explain non-obvious decisions.

    Deliverable

    A focused code change

    Review checkpoint

    Test failure paths, permissions and untrusted input.

  4. Run formatting, static analysis, unit, integration, security and regression checks appropriate to the risk.

    Deliverable

    A recorded verification result

    Review checkpoint

    Reject unrelated refactors hidden inside the change.

  5. Complete human code review, deployment review, monitoring and rollback preparation before release.

    Deliverable

    An approved release and rollback plan

    Review checkpoint

    Monitor the deployed behaviour against the acceptance criteria.

Adapt, do not paste blindly

Working prompts for this recipe.

Replace bracketed placeholders, supply approved sources and remove unnecessary personal or confidential information.

Working prompt

Use this only after replacing every bracketed placeholder and removing unnecessary sensitive information.

Review the code task below and the supplied repository context. First restate acceptance criteria, identify affected components, security boundaries, tests and unknowns. Then propose the smallest change plan. Do not write code until missing information is listed. Preserve existing behaviour outside scope and never request or expose secrets.\n\nTASK:\n[TASK]\nCONTEXT:\n[APPROVED CODE CONTEXT]

Final review prompt

Use as a second-pass checklist, not as approval to publish.

Review the draft against this intended outcome: Move an AI-assisted code change from a clear requirement through security, testing and accountable human approval. List unsupported claims, missing evidence, ambiguous language, privacy concerns, accessibility issues and actions that still require human approval. Do not rewrite the draft until the issues are listed separately.

Human review required

Verification and cautions

  • Verify names, figures, quotations and source claims before use.
  • Remove confidential or personal information unless the selected service and account are approved for it.
  • Keep a named person responsible for the final decision and published output.

Keep the outcome, change the method

Practical alternatives

Implement the change manually using the same review and test controls.
Use a security or specialist engineering review for authentication, payments, cryptography or sensitive data.