Skip to main content
When a deploy fails, you don’t have to read the build log alone. The platform agent — Korve’s built-in diagnostician — analyzes the failed deployment and returns a structured diagnosis: what broke, why, and a concrete suggested fix.

Asking for a diagnosis

API: POST .../deploys/{deployId}/diagnosis — see the Deploys API. MCP: await korve.deploys.diagnose({ orgId, projectId, deployId }). Only failed deployments are diagnosable (409 otherwise). The first call produces the diagnosis; it is then cached, so repeat calls are free and instant — the response carries cached: true.

What it sees

The platform agent reasons over the failed deploy’s build log and recorded error, the project’s runtime class, recent deployment history (flaky vs persistent failures), and the names of configured environment variables. Env var values are never read — they stay encrypted; the agent only knows which keys exist (enough to notice a missing DATABASE_URL).

The diagnosis shape

The shape is strict and validated — agents can branch on kind and confidence without defensive parsing. A retry kind with decent confidence means: just deploy again.

Cost

Each fresh diagnosis meters agent.diagnosis ($0.20/run on the rate card); cached reads are not re-metered. Diagnosis requires active billing.