Build a PR dashboard across multiple repos
They used ChatGPT for planning and an agent in WebStorm to assemble a dashboard that tracked pull requests across four Azure DevOps repos.
- What they did
- They first asked ChatGPT 5 for an architecture, then handed that output to Junie in WebStorm to draft a Readme and project rules. From there, they had the agent build the app in stages: the page layout, placeholder records, Azure API work, YouTrack hookup, and the remaining features. They kept personal access tokens on their machine, reviewed the code as it was produced, and suggested changes rather than editing it directly.
- How it went
- In about 3 hours, the dashboard had three views and was well received by the team. Another hour added their requested tweaks, and the team started using it every day. Most steps worked right away, though Junie sometimes repeated itself or became inconsistent.
- Tips
- For a larger codebase, add a step that pushes reuse and keeps configuration in one place. Treat the agent as a builder you supervise, especially when working with sensitive access and generated code.
Try it yourself with Cursor
You are helping me build a local dashboard for pull requests. First, propose a simple architecture for a tool that reads open PRs from my [Azure DevOps/GitHub] repos: [repo 1], [repo 2], [repo 3], and [repo 4]. Then, build it in small steps: app shell, mock data, API integration, status flags for approvals/conflicts/comments, and any optional integration with [YouTrack/other tool]. After each step, stop and show me the result so I can approve before you continue. Do not send anything, merge anything, delete anything, or change any existing PRs. Keep access tokens and secrets on my machine only. Focus on readable code, shared helpers, and centralized config.
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
Use an AI spec to brief a coding agent
Work out a feature with an AI assistant, then pass the spec to a coding agent and verify the result by testing.
Use ChatGPT to narrow down Swift error causes
A Swift developer pastes an error and nearby code into ChatGPT to get a quick first guess, then checks the output before changing anything.
Draft a minimal Windows VNC viewer from a brief
They asked Claude to build a tiny Windows 10 VNC client from an email spec, but after a week it still did not work.
Use an agent to patch a stubborn app bug
They pointed a coding agent at two annoying software behaviors and had it debug one and add a self-improvement feature to the other.
Have agents co-build a reference system with role splits
A solo founder divided an AI-assisted build into roles and shipped a 120-model mental-models framework with an MCP server.
Move a Chrome extension into Safari
A developer had ChatGPT rewrite Session Buddy from Chrome for Safari and get it working in roughly 20 minutes.