Prime Edge AI: intelligence that knows where to think.
Not every health question is the same size. Prime Edge AI decides where each one is answered.
Last updated
Technology brief, September 2026
How it works
A router on the device reads each question before anything leaves the device, and chooses where it is answered.
- Routine tasks stay on the device. Daily check-ins, meal logs and routine readings are answered by Apple's on-device model, through its Foundation Models framework: offline, and with no cost per call.
- Harder questions go to the cloud, only when needed. Years of history, clinical literature and live search go to a frontier model in the cloud.
The person sees one conversation and never the handover.
Security
- Every device attests itself in hardware.
- No key ships in the app.
- Access tokens expire hourly and carry no identity.
Why it matters
Privacy by architecture. Routine processing never leaves the handset. Escalated questions go straight to the model, with no intermediary.
Economics that scale. Requests answered on the device have no cloud cost. Spend tracks difficulty, not headcount.
Why Apple first
Apple silicon offers fast on-device processing, and one Foundation Models framework spans iPhone, iPad, Mac and Watch.
What comes next
Android, using Google's on-device foundation models.
Where it runs
Prime Edge AI is built into Averra, the digital health twin we are developing.