AI code review
Using an LLM to comment on, summarise or approve pull requests — the fastest-growing AI surface after code generation.
AI reviewers read the diff and flag bugs, style issues and missing tests, either as a first pass before a human or as the only reviewer for low-risk changes. Google reports over 8% of code-review comments internally are now resolved with AI assistance. It is the main lever teams use against the review bottleneck, but it inherits the models' security blind spots.