Skip to main content

Offline evals versus database row gates

Offline eval suites score model outputs in isolation. Database row gates instead verify whether declared tool parameters line up with persisted rows using read-only SQL at verification time—catching ROW_ABSENT even when eval scores look strong.

Use /integrate to wire structured NDJSON observations into your environment, then use /pricing when you need commercial metering for API-backed verification runs in CI.

What to do next

  • Start first-run on /integrate before you expand eval coverage.
  • Compare bundled proof at /examples/wf-missing.
  • Read /pricing for commercial packaging when eval infrastructure needs API keys.
  • Review /security for how verification credentials are scoped.