Point your OpenAI client at a model that can't read your prompts — and check that before the first request Developers Nukri Basharuli and George Zhgenti released Gatekeeper, a local verification proxy that lets OpenAI SDK applications route requests to Super Protocol's Confidential Router with only a base_url change. Before each request and every five minutes thereafter, Gatekeeper runs six attestation stages — including certificate-chain root checks inside AMD SEV-SNP or Intel TDX confidential VMs and TLS fingerprint binding — and returns a 503 error if any stage fails. The tool pins a deployment's evidenceDigest so that new versions require explicit user approval before traffic is forwarded. By Nukri Basharuli and George Zhgenti Here's a setup we see a lot. A claims team at an insurer has a working prototype on the OpenAI SDK that writes a short summary of each claim file. Then legal asks who else can see the claim text while the model is running. For any hosted API, the honest answer is the provider and whoever operates the GPUs, at least technically. The contract and the retention policy say they won't look. You have no way to check. This post shows how to move that prototype to Confidential Router with almost no code changes, and how to verify where your data is going before every request. Router speaks the standard OpenAI API. In Python you change base url : python from openai import OpenAI client = OpenAI base url="http://127.0.0.1:8787/v1", local Gatekeeper api key="sk-tee-v1-...", resp = client.chat.completions.create model="