Run bot crews that clean up CI and open PRs

A SpaceXAI engineer used five Grok bots to watch for breakage, dispatch fixers, and leave ready-to-review pull requests by morning.

Done with Grok BotΒ· AdvancedΒ· Sep 2026

What they did
Lingxi split the work across five Grok bots focused on iOS and mobile, desktop, Android, infrastructure, and harness tasks. Those bots could start cloud coding agents, read their transcripts and screenshots, and update a shared Notion database for pull requests. Every half hour, they checked for broken CI, security problems, and merge conflicts, then either sent agents back to repair them or kicked off reviews. Jenny, the operations bot, handled early-morning one-on-ones, postmortems, and updates to the playbook.
How it went
The setup let the team run more than 200 agents at the same time, instead of Lingxi’s manual cap of 15. Overnight checks regularly left new pull requests ready for review each morning. Related Grok Bot work also produced more than 2,000 pull requests in a month and cut multi-week features down to weeks.
Tips
This works best when each bot has a narrow job and a shared place to track status. Keep a human approval step before any merge, deployment, or other irreversible action.

Try it yourself with Grok Bot

Monitor [repo or project] for failing CI, security alerts, and merge conflicts. Use separate agents for each issue, assign them to investigate and propose fixes, and write results to [tracking system]. After each fix, open a pull request and ask [person or team] to review it. Before merging, deploying, deleting, or submitting anything, stop and ask me to approve the next step. At the end, send a short summary of what was handled, what is still open, and which PRs are waiting for review.

Fill in the [brackets]. Agents can make mistakes, so review anything before it is sent, paid or deleted.

Read the original on x.com β†—

4 more reports of this

Get 3 agent uses like this every morning

With the day's top AI news. Free, and one click to unsubscribe.