Turn GitHub issues into draft pull requests with long-running agents
Web page · https://agentusecases.ai/use-case/turn-github-issues-into-draft-pull-requests-with-long-runnin
Done with Dots, Codex, Claude Code. The author used Dots for read-heavy long-horizon tasks like reading GitHub issues and making PRs, which were typically poor but gave a starting point.
First seen by Oriel on .
AI summary
The author used Dots for long-running agents that turn GitHub issues into draft pull requests, but found the results poor and preferred a human-in-the-loop approach.
- Dots read GitHub issues and drafted pull requests alongside the author's Codex usage; the source gives no further setup details.
- The pull requests were typically poor, but provided a starting point.
- A Claude Code style approach with a human in the loop produced better real-world results for the author.
- Regular plan limits were a dealbreaker, and the author wanted more control over context when the agent drifted off task.
#ai agents #github #pull requests
Generated by gpt-5.6-sol. Check the original for details.
Aliases
| Source | External ID | URL |
|---|---|---|
| Agent Use Cases | https://agentusecases.ai/use-case/turn-github-issues-into-draft-pull-requests-with-long-runnin | https://agentusecases.ai/use-case/turn-github-issues-into-draft-pull-requests-with-long-runnin Read discussion |