Verify
Don't Trust Our Privacy Claims.
Verify Them.
RedPill exposes nonce-bound attestation reports, upstream verification, signed receipts, and attested sessions so privacy is a cryptographic evidence chain, not a policy promise.
AI privacy today is too often a trust-me promise.
Policy Promises
Most AI privacy claims depend on contracts, settings, and logs you cannot independently inspect.
No Hardware Evidence
Without attestation, you cannot prove which workload handled your prompt or which keys it controlled.
Weak Audit Trails
Privacy reviews need repeatable evidence: request hashes, route records, signed receipts, and attested sessions.
Policy Promises
Most AI privacy claims depend on contracts, settings, and logs you cannot independently inspect.
No Hardware Evidence
Without attestation, you cannot prove which workload handled your prompt or which keys it controlled.
Weak Audit Trails
Privacy reviews need repeatable evidence: request hashes, route records, signed receipts, and attested sessions.
Verify Each Step of Confidential Inference
Fetch the report, receipt, and attested session; then verify the evidence locally instead of trusting a server-side claim.
What ACI Proves Depends on What You Verify
The gateway produces evidence. The relying party still has to check that evidence locally or through shipped artifact verification tooling.
Plain OpenAI SDK
The call works like a normal API call. Evidence can be generated and audited later, but no mismatch is rejected in the moment.
Artifact Verification
A relying party verifies gateway identity, channel binding, upstream verification, receipt signature, and response hashes.
ACI E2EE
Selected request and response fields are encrypted to a key from the attested keyset, so non-TEE nodes see ciphertext.
Honest Boundaries
ACI cannot make an arbitrary upstream confidential; the adapter must verify provider identity and enforce channel binding.
Optional middleware sees plaintext after gateway decryption and must be inside the same attested deployment and audit boundary.
Receipts are implemented with configurable TTL, but durable public transparency logging is not implemented yet.
Trust-Me AI vs Prove-It AI
Privacy policies are useful. Receipts, channel bindings, and audit sessions are testable.
Standard AI API
Plain hosted inference
Privacy-Policy AI
Promise-based privacy
RedPill
Cryptographic evidence
Built for Professionals
For industries where confidentiality isn't optional, RedPill delivers AI that respects your professional obligations.
- For Lawyers
- For Healthcare
- For Finance
- For Executives
Open Source Where It Matters
Audit the gateway, run the verifier, inspect the chat UX, and track the ACI signed-receipts spec as a developer-preview proof layer.
Get an API key in 2 minutes
Start with the OpenAI SDK, choose a confidential model, and add verifier checks when you need audit-grade proof.
Get API Key
The confidential AI cloud: verifiable inference with attestation reports, signed receipts, audit sessions, and E2EE paths.