This page lists the controls built into Pragence today, the outside services it can use, and what we don’t claim yet. Ask us for anything you need for your own review.
Some controls are always on. Others, like multi-factor sign-in and IP allow-lists, have to be enabled for your organization or deployment.
We run Pragence for you. Tell us your data residency and model requirements during setup, and we’ll confirm what we can meet before you commit.
Run Pragence on your own infrastructure with Docker or Helm, with your own database, secrets and model accounts. Your team controls access, backups and network rules.
Text models from OpenAI, Azure OpenAI, Anthropic or Gemini. Voice runs on Gemini Live. You decide which providers see your data.
Pragence only sends data to a provider when you switch on the feature that uses it.
Pragence does not hold SOC 2, ISO 27001, HIPAA or GDPR certification today. We won’t show a badge until there’s an audit behind it.
What we can do now: walk your security team through the controls above, answer your questionnaire against the actual code, and describe how a specific deployment is configured.
Email security@pragence.com with what you found and how to reproduce it. Please give us a reasonable chance to fix it before sharing it publicly. We’ll reply to confirm we’ve received it.
30 minutes. Bring a real question and the document that answers it. We’ll show you the answer on chat, voice and WhatsApp, the citation, and what happens when the answer isn’t there.