Collection · 4 use cases
For developers
Feedback in, reviewed fixes out: bug reports, pull requests and issues, with Codex doing the heavy lifting and you merging.
OpenAI’s developer example is the clearest picture of what a dot can own: it watches feedback, scopes fixes, builds and tests them, and brings you pull requests to review. These prompts set that up step by step. For cloud coding work, create the Codex cloud environment first.
Suggested order. Start with the pull request digest and issue triage, which only read GitHub and report to you. Once those summaries are useful, add Slack bug-report monitoring, then let your dot prepare fixes for review.
Keep humans on the merge. Fixes arrive as draft pull requests, which are visible to everyone with access to the repository. Review each one like any contributor’s change, and keep merging, deploying and closing issues with you. Connecting Slack alone doesn’t start monitoring: ask your dot to confirm which events it can follow.
-
Fix reported bugs for review
Your dot works through bug reports, reproduces each one in Codex, and opens a draft pull request with the fix for you to review.
-
Watch Slack for bug reports
When a new bug report lands in a Slack channel, your dot investigates it and prepares a fix for your review, without posting in the channel.
-
Open pull request digest
Every weekday morning your dot checks open pull requests in your repo and lists what waits on you, what's stale and what's failing.
-
Triage new GitHub issues
Each weekday your dot reads new GitHub issues and sends you a list with suggested labels, likely duplicates and a one-line repro.