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.
An autonomous ReAct agent that queries real data to stop cloud outages before they occur, built for the Sanity Challenge.
An autonomous ReAct agent that queries real data to stop cloud outages before they occur, built for the Sanity Challenge.
SHIPCHECK is a ReAct agent connected to a Sanity Content Lake through MCP. Given a proposed upgrade, it calls four tools for component state, version constraints, cluster dependencies and a knowledge graph. It follows two-hop dependencies with GROQ and settles conflicting docs by an authority score from 1 to 10. Sanity held 18 seeded records.
For the payment service v2 to v4 upgrade, it ran 13 steps and found that the cluster's Payment SDK v2.4.1 was below the required v3.0.0. It returned DO NOT SHIP YET, and a simulated SDK fix flipped the verdict to safe.
The data is a small seeded set of 18 records, and the claim that hallucination fell from about 30% to 0% is stated without any evaluation method.
Using the logs and metrics export at [path], look for patterns that came before past outages, like rising error rates, saturated CPU, or expiring certificates. Write a script that checks current data for those signals and outputs a ranked list of risks with evidence. Finish when it runs on my sample data. Do not change any infrastructure.
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.