Resolve a Slack-reported issue with a coding agent
A Codex agent resolved an issue passed to it in about 40 minutes, and an ops agent verified the fix back in Slack.
Done withCodex
- What they did
- An internal ops agent called “claw” triaged an issue reported in Slack. A person then handed the issue to a Codex agent, which worked independently to resolve it. The ops agent later posted verification of the fix back into the same Slack thread.
- How it went
- The Codex agent resolved the issue after 40 minutes, with the ops agent confirming success in Slack. No shortfalls or additional metrics are stated.
- Worth knowing
- Relies on internal purpose-built “claw” ops agent tied to Slack; took 40 minutes end-to-end.
Try it yourself with Codex
Here is an issue from my team: [paste issue text or link] in the repo at [repo path or URL]. Find the cause, make the fix, run the tests, and open a pull request with a short summary of what changed and how you checked it. You're done when tests pass and the summary is ready for me to review. Don't merge or deploy anything, and pause to show me the diff before pushing.
Source: X · Jul 23, 2026
Five of these in your inbox every morning
The best things people got an AI agent to do, each with the prompt to try it.
More like this
Turn tickets into merged pull requests
Pulls tasks from GitHub Issues or Linear, then runs Claude Code or Codex in isolated Kubernetes pods to carry each one through to a PR.
Recommend a hotel from client notes using Codex
A travel advisor had Codex use client notes to recommend a Belmond hotel in Italy, checking live booking engines and generating a detailed Word doc.
Diagnose a killed process on a server
Codex CLI over SSH found the OOM killer in kernel logs on a 2 GB droplet with no swap and listed fixes by risk without changing anything.
- Claude
Build a C compiler with a team of parallel agents
Anthropic's engineering write-up on tasking Opus 4.6 agent teams with building a C compiler.
Configure a local AI lab and build a knowledge graph by chat
Users had Hermes Agent set up a local AI stack (liteLLM, Postgres, Prometheus, Grafana) and install Gbrain as an MCP server to build a personal knowledge graph.
Click through apps to verify its own work
With computer use, Devin built and played a desktop game, ordered on Amazon, and tested its own work by clicking through the app.