Safety infrastructure for healthcare AI
Your safety evidence expires every time your model changes.
Independent, clinician-calibrated evaluation for AI in healthcare. Sesh stress-tests your agent the way your hardest patients do, grades what it said, and hands you the evidence — on a cadence, not once.
What we build
Sesh Platform
Independent, clinician-calibrated safety evaluation for AI in healthcare. A custom-built attacker, judge, and guard stress-test your agent, grade what it said, and hand you the evidence — on a cadence, not once.
See the platform →Sesh Arena
Help make AI in healthcare safer. Try to break fictional AI agents built for care settings. Nothing real gets ranked.
Enter the arena →Sesh app
You forget half your therapy session within 24 hours. Sesh gives you an AI that understands what you talked about, so the work doesn't stop when the session does.
See the app →Who builds it
A decade of AI in healthcare — ML lead at Headspace Health, research at NYU Langone and Northwell — and an NBC-HWC certified coach who has sat with clients. In clinical safety, the clinical judgment is the scarce half. It’s the half this is built from.
See what your safety layer is missing.
A scoped evaluation against your live agent — you see what we found before anything changes.