Coordinate sub-agents to monitor PRs and fix prod bugs
A Cursor Projects coordinator agent delegates to sub-agents, watches new PRs and production bugs, spins up agents to fix issues, and surfaces questions to the user.
Answer.AI testers found Devin completed only 3 of 20 tasks, succeeding at moving Notion data to Google Sheets and building a planet tracker.
Answer.AI testers found Devin completed only 3 of 20 tasks, succeeding at moving Notion data to Google Sheets and building a planet tracker.
Three Answer.AI data scientists (Hamel Husain, Isaac Flath, Johno Whitaker) gave Devin 20 tasks. Devin takes commands through Slack and works in a Docker container with a terminal, browser, code editor and planner. Early tasks included pulling data from a Notion database into Google Sheets and building a planet tracker for checking historical Jupiter and Saturn positions.
Devin finished 3 of 20 tasks: the Notion-to-Sheets move, the planet tracker, and a Discord bot research task. Three were inconclusive and 14 failed. Simple-looking tasks often took days, and it was hard to predict which would work.
Devin starts at $500 per month. It kept pushing on impossible tasks, such as a Railway deployment, for over a day instead of stopping, so set time limits.
Pull the data from my Notion database [database name or link] into a new Google Sheet, with one column per Notion property and one row per entry. Keep the Sheet in a shared location I can open, and tell me the link when the row count in the Sheet matches the Notion database. Ask me before overwriting or deleting anything that already exists.
A Cursor Projects coordinator agent delegates to sub-agents, watches new PRs and production bugs, spins up agents to fix issues, and surfaces questions to the user.
Ran a Cursor agent continuously for 24 hours to build a project management tool; the app fully works but is not production ready.
The author had ChatGPT take the Session Buddy extension source from Chrome, port it to Safari and install it, taking about 20 minutes.