Build a project management tool with a 24-hour agent run
Ran a Cursor agent continuously for 24 hours to build a project management tool; the app fully works but is not production ready.
Done withCursor
- What they did
- The agent ran Sonnet 4.5 from the Cursor CLI in a continuous loop for 24 hours, receiving only the prompt "build a project management tool" and almost no upfront context. It tracked its own progress and iterated autonomously until it determined the task was complete. The human started the loop but added no further input during the run.
- How it went
- The resulting app fully worked as a project management tool. It was not production ready, though the code structure and navigation proved better than expected.
- Worth knowing
- Almost no initial context was supplied, showing how far a simple looped prompt can go on its own.
Try it yourself with Cursor
Build a project management tool in this repo with [features: tasks, boards, assignees, due dates] using [tech stack]. Work in stages, run the tests and the app as you go, and keep a running list of what works and what is missing. Stop when the core flows work end to end and give me a summary of known gaps; ask before deleting files or adding paid services.
Want help getting this working? Join the Vibe Coding Academy ↗ Run by Alex Finn, who also runs this site.
2 more accounts of this
Source: X · Oct 14, 2025
Related use cases
Keep coding agents running autonomously for long stretches
Cursor's write-up on scaling long-running autonomous coding.
Draft personalized outbound, recaps and forecasts for sales
Cursor's internal ChatGTM drafts signal-based outbound messages with personalized landing pages, call recap emails and follow-ups, and assembles the deal forecast.
Debug prod pods and docker-compose with Cursor
A DevOps engineer uses Cursor with a Kubernetes MCP to pull prod logs and suggest fixes, and to repair a broken docker-compose file.
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.
Triage issues and open fix PRs with a GitHub bot
A cookbook shows a GitHub bot that triages issues, reviews PRs, answers questions with citations, flags AI-slop contributions, and opens patch PRs for human review.
Custom agent
Test features on screen and merge fixed PRs
Ryan Carson uses Devin's Test App feature to record and narrate feature clicks, fix bugs, and merge PRs with a !land command.
Get 5 like this every morning
The best things people got an AI agent to do, each with the prompt to try it.