Route code or system-design work to the right review path.
AI coding and engineering review
Use this page when the main problem is AI-assisted code review, refactor planning, test coverage, architecture boundaries, or implementation checks against official guidance.
Core workflows
Choose the engineering review workflow that matches the code or implementation problem you need to solve now.
-
-
Use this when a proposed change may cross module, layer, API, or ownership boundaries.
-
Use this when code needs to be checked against official language, framework, or platform guidance.
-
Use this when changes need test coverage and regression-risk review before delivery.
When to use AI coding and engineering review
-
Use this page when AI is helping with code review, refactor planning, tests, or implementation checks.
-
Use it when you need to check whether generated code follows the current project architecture.
-
Use it when you need to identify regression risk before accepting a code change.
-
Use it when the output must be checked against official language, framework, or platform guidance.
Before you start
-
Identify whether the task is code review, refactor planning, test coverage, architecture review, or implementation validation.
-
Keep behavior-preserving changes separate from redesign or architecture changes.
-
Verify framework, language, and dependency assumptions before accepting AI-generated code.
Also relevant in
-
Prompt engineering The main problem is the prompt, output contract, source boundary, or reusable prompt component.
-
AI assistants The main problem is assistant product behavior, memory, browsing, or configuration.
-
Agents and workflows The main problem is orchestration, routing, memory, or multi-step system behavior.
-
API integrations and tools The main problem is SDK/API wiring, tool calls, web access, or external systems.