How it works

Three lines of code. Zero trust required.

Wrap one function with the SDK. Every AI call gets hashed, graded, and chained automatically — you watch it live in the desktop app, and hand your auditor a proof they verify without trusting you.

your_app.py

$ pip install foxy-audit

from foxy_audit import audit

@audit(policy="soc2")          # the only line you add
def ask_model(prompt):
    return llm.generate(prompt)   # your code, unchanged

That decorator is the only change to your app. It never blocks your function and never throws its own errors — everything below runs on a background thread.

Hashed on your machine

The moment your function returns, Foxy takes a SHA-256 of the prompt and response and throws the raw text away. Only the digests, token count, and policy tag leave your servers — your data never does.

Graded against your policy

Every call is scored in real time against the policy you tagged — HIPAA, SOC 2, or your own rules. Anything that crosses the line is flagged the instant it happens, not in a review weeks later.

Sealed into a hash chain

Each record's hash folds in the one before it — and which model produced it. Edit any past entry and every hash after it stops matching. Tampering isn't hidden; it's mathematically obvious.

Watch live, prove anywhere

The desktop app reacts the instant a call lands — green when it's clean, red on a breach. The dashboard shows the whole trail and exports a compliance passport your auditor re-verifies themselves, mapped to NIST AI RMF & the EU AI Act.

See it on your own stack.

Book a walkthrough and we'll wire the SDK into a real call live, then verify the chain in front of you.

Book a demo