Why We Built Our Own Background Agent

Zach Bruggeman, Jason Quense and Rahul Sengottuvelu on Inspect, the background coding agent Ramp built in-house. The point they keep returning to is verification: Inspect writes code like any other agent, but it also has the context and tools to prove the code works. On the backend that means running tests, reading telemetry and querying feature flags; on the frontend it means screenshots and live previews. Their line for it:

Agents should have agency, and so we made sure Inspect is never limited by missing context or tools, but only by model intelligence itself.

Each session gets a sandboxed VM on Modal with a full local-equivalent dev environment, wired into Sentry, Datadog, LaunchDarkly, Braintrust, GitHub, Slack and Buildkite. Repository images rebuild every 30 minutes and sessions restore from a snapshot, so a checkout is at most half an hour stale and startup is close to instant. Sessions are cheap enough to run several against the same prompt and pick the winner. About 30% of pull requests merged to their frontend and backend repos are now written by Inspect, reached in a couple of months without anyone being told to use it.

Most of the post is a build-it-yourself spec rather than a product pitch, and it is specific about the parts: OpenCode as the underlying agent because it is server-first with a typed SDK, Cloudflare Durable Objects with a SQLite database per session for the API, and clients in Slack, the web, a Chrome extension and pull request threads. The Slack entry point uses a fast model to classify which repository a message is about, which they say is what lowers the barrier for non-engineers. They also make a case for multiplayer sessions, where several people prompt the same session and each change is attributed to whoever asked for it.

The argument worth keeping is the last one: owning the tooling beats buying it because it only has to work on your code. Same team, different experiment, in 100 vulnerabilities patched with no humans.