AI first-pass review on open pull requests
Reads the diff of each open pull request, has AI note the obvious problems, and posts them as a comment.
What it does
Each integration step this workflow runs, in order, what it is for, and the conditions and loops that decide when it runs.
For each
pullRequest- 1
OpenAIQuery modelAsks the AI to list what is plainly visible in the diff: missing error handling, unclear names, untested behaviour and obvious risks. - 2
GitHubCreate commentPosts the points as a comment on the pull request, noting how many changed files were read and that nothing is approved. - 3
GitHubAdd label to issueAdds the 'first-pass-reviewed' label to the pull request after commenting, so later runs skip it until the label is removed.
- 1
How it works
What happens on each run, in plain English.
Every hour, the open pull requests in one GitHub repository are checked and each one not yet reviewed gets a first pass: its changed files are fetched, the AI is asked to note what is plainly visible in the diff, such as missing error handling, unclear names or new behaviour without a test, and those points are posted as a comment.
The reviewer starts from something rather than nothing. The comment says it is a first pass, and nothing is ever approved, merged or closed. Each pull request is reviewed once: after commenting, a label is added and anything carrying it is skipped, so a re-run never posts the same review twice; remove the label to have it looked at again. Drafts are left alone, and on a large pull request only the first batch of changed files is read, with the comment stating how many it covers.
You need a GitHub token that can read the repository, since the changed files are read from GitHub's API directly, and the label must already exist in the repository.
Start from a workflow that already works.
Add "AI first-pass review on open pull requests" to your workspace, connect its apps, and make it yours. No credit card required.
Free plan available · No credit card required
