What can you configure
Qodo works out of the box with sensible defaults, but its behavior can be customized to match your team’s standards and workflows. Configuration controls things like:- When reviews run (manual or automatic)
- Where feedback appears (summary, inline, or both)
- How strict or verbose reviews should be
- What content should be ignored
Run a code review
Qodo can review pull requests in two ways: manually or automatically. Both approaches produce the same review experience and findings. The difference is when and how the review is triggered.While a review runs, Qodo posts a temporary “review in progress” comment so you know Qodo is processing the request. The comment is removed once the review is posted. If the run fails or is superseded by a newer run, the comment is updated to reflect the change. Admins can disable this with the In-progress comment setting.
Run a review manually
You can request a review directly from the pull request by adding a comment:- Qodo acknowledges the request with a 👀 reaction
- The review is generated and posted directly in the pull request
- Feedback appears based on your configuration (summary, inline, or both)
- You want to review on demand
- You’re testing configuration changes
- You don’t want reviews to run on every pull request update
Re-running a review does not clear findings from previous runs. When Qodo detects that a finding has been resolved, it strikes through the finding. Findings that are no longer valid for other reasons, such as a fix made in a related repository, are not struck through and remain until you dismiss them manually.
Run reviews automatically
Qodo can also run reviews automatically when pull requests are opened or updated. Automatic reviews are controlled by the Code review trigger setting in the Qodo portal, or using the.pr_agent.toml file, and allow Qodo to:
- Run reviews when a pull request is opened, reopened, or marked ready for review
- Optionally, update the existing review comment on every new commit pushed to the pull request, instead of only at publish time (see Persistent review comments)
- Keep review feedback in sync with the latest code changes
- Consistent review coverage
- Less manual intervention
- Faster feedback loops