Use Copilot to handle small site edits in draft PRs
A developer handed GitHub Copilot two minor website tweaks and got back separate draft pull requests that were easy to test and merge.
- What they did
- They turned on the agent in their Angular site repository using a Copilot Pro+ or Enterprise account. For two GitHub Issues they had written with detailed acceptance criteria, they asked Copilot to fix footer links and tighten the filter-bar spacing. Copilot cloned the repo, laid out a plan, committed the changes on branches, opened draft pull requests, and recorded its progress while the author checked each branch locally.
- How it went
- Both pull requests passed review and were merged. In the footer change, the agent picked appropriate routes without being told exactly where to send the links. In the spacing change, it reduced padding in two CSS classes by about 28px total, and the layout still looked fine. They only tried straightforward tasks.
- Tips
- Clear issue descriptions made the handoff smoother. This preview uses GitHub Actions minutes, and it requires a Pro+ or Enterprise plan.
Try it yourself with GitHub Copilot
In my repository [owner/repo], make these two small website changes: [change 1] and [change 2]. For each task, create a separate draft pull request with a brief note explaining what you changed and why. Do not merge, delete, or submit anything irreversible; stop after both draft PRs are ready and ask me to review before taking any further action.
Fill in the [brackets]. Agents can make mistakes, so review anything before it is sent, paid or deleted.
1 more report of this
Get 3 agent uses like this every morning
With the day's top AI news. Free, and one click to unsubscribe.
Related agent uses
Break a runtime migration into tiny reviewable PRs
GitHub engineers had Copilot agents carry out most of a large TypeScript-to-Rust runtime rewrite.
Run terminal commands carefully in Copilot agent mode
A VS Code user had Copilot agent mode run shell commands, but it often missed output or got stuck until they changed the shell setup.
Run Copilot CLI in loops and split multi-part work
Daniel Ward used GitHub Copilot’s autopilot and /fleet features to finish larger jobs and divide separate chunks across parallel agents.
Set Copilot to code in a branch before it pushes
A developer used GitHub Copilot to work issues, but learned to give tighter instructions after it wrote weak first PRs and pushed to the wrong place.
Use Devin to push backlog work into pull requests
Ryan Carson used Devin across several tools to turn backlog items into pull requests faster.
Let an AI agent inspect a Windows crash dump
Use MCP to give an AI agent structured crash details from a Windows dump so it can track down the fault and propose a fix.