Skip to main content

Healthy infrastructure is not enough

A candidate may be ready, fast, and error-free while producing worse answers. InferCrane accepts aggregate evidence from a customer-owned evaluation suite, verifies its signature and revision identity, and lets Release Guard enforce explicit score thresholds. InferCrane does not store prompts or generated outputs in this evidence format and does not choose an LLM judge for you.

Create an evaluator key

Keep the private Ed25519 key outside the control plane. The operator authorized to attach evidence is the trust boundary.

Ingest a result from any evaluator

Have Ragas, DeepEval, a custom CI evaluator, or another customer-controlled system emit the strict content-free evaluator result contract:
evaluator-result.json
Bind that aggregate result to the exact immutable candidate revision, sign it, and explicitly attach it through the control-plane API:
Unknown fields are rejected, so prompt and generated-output bodies cannot accidentally enter the evidence envelope. If API attachment fails, the signed local file remains available for a safe evaluation attach retry.

Sign aggregate evidence directly

The signed payload records deployment, immutable revision, suite and evaluator versions, normalized score, pass/fail result, sample count, result-artifact digest, and evaluation time. Attaching the same evidence twice is idempotent.

Fail closed in Release Guard

Active and candidate evidence must use the same suite version and evaluator version to be comparable. Missing or incomparable required evidence leaves the decision waiting. A failed suite, score below the minimum, or regression beyond policy rejects the candidate. The evaluator cannot activate a revision; promotion remains a separate, authorized control-plane decision.
An artifact digest proves which private result bundle was evaluated, not that the evaluator was well-designed. Teams remain responsible for representative datasets, evaluator calibration, privacy, and human review of high-risk changes.