Foxy Audit
Book a demo
← Back to all cards

Metadata Policy Judge

An optional judge reviews captured metadata.

Capture comes first. The judge then evaluates non-content metadata against your policy and records an honest review signal without receiving raw prompts or responses.

For interactions captured through the SDK, a configured judge evaluates the recorded metadata and returns a verdict such as clean, flagged, or unavailable. It is an operational review signal, not a compliance certification, and its verdict remains linked to the tamper-evident audit record. You choose which model judges your workspace and — depending on your plan — whose API key pays for those model calls.

What it does for you

Which judge, and whose key pays for it

You pick the model that grades your workspace — Google Gemini, OpenAI, or both (each record graded twice; a breach found by either wins). You also pick whose provider key pays for those model calls, and that part depends on your plan:

To say the quiet part out loud: audit-event credits are not model tokens. Your plan buys capture, chaining, anchoring, exports and verification. Unless you are on Premium using our managed keys, the AI judge runs on your provider account and appears on your provider's bill.

A key you store is encrypted before it is written down, decrypted in memory only for the moment a verdict is produced, and never returned by our API, written into your audit chain, or included in an export — the dashboard can only tell you that a key is set, never show it back to you.

If no key is configured and you are not on managed keys, nothing is faked: those records fall back to deterministic metadata checks and are labelled as such, so an unavailable judge reads as an honest unknown rather than a clean pass.

See the judge catch a breach.

Book a demo and we'll run a policy-violating call and watch the flag fire in real time.

Book a demo