Catch cloud outage risks before they happen
An autonomous ReAct agent that queries real data to stop cloud outages before they occur, built for the Sanity Challenge.
Done with a custom-built or unnamed agent
- What they did
- 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.
- How it went
- 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.
- Worth knowing
- 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.
Try it yourself with Claude Code
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.
Source: DEV · Sep 26, 2026
Five of these in your inbox every morning
The best things people got an AI agent to do, each with the prompt to try it.
More like this
- Claude
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.
- Custom agent
Add agentic forgetting to an agent's memory
Someone implemented a rudimentary version of Tim Kellogg's agentic forgetting approach and reports it works impressively even in its simplest form.
Hand narrow code changes to Devin for pull requests
A team used Devin for a month on small fixes like chart formatting and API edge cases, with tests and PRs; a complex full-stack task went poorly.
Migrate toolchain, architecture and site design with Claude Code
A developer had Claude Code switch a monorepo to oxlint/oxfmt, restructure the architecture and redesign a site, validating in a loop; the redesign took days instead of weeks.
Build and deploy a Game of Life simulation site
In a vendor launch demo, Devin built an interactive Game of Life website, added requested features step by step, and deployed it to Netlify.
Resolve a Slack-reported issue with a coding agent
A Codex agent resolved an issue passed to it in about 40 minutes, and an ops agent verified the fix back in Slack.