The AI teammate that proposes the next version. Eri is our AI domain expert and the knowledge coach in the loop. It builds the program from the driver's goal, reviews the session record and proposes exact, versioned changes for that operator. By default, nothing changes until the operator approves it. A catalog's autonomy policy can allow scoped changes.
Modeled view.
Eri is our AI domain expert and the knowledge coach in the loop. It builds the program from the driver's goal, reviews the session record and proposes exact, versioned changes for that operator. By default, nothing changes until the operator approves it. A catalog's autonomy policy can allow scoped changes.
Eri is our AI domain expert and the knowledge coach in the loop. It reviews the session record and proposes exact, versioned changes for that operator. By default, nothing changes until the operator approves it. A catalog's autonomy policy can allow scoped changes.
Modeled example.
A patch applies only with trusted and fresh source quality, remaining recursion budget and a passed cooldown. Model output cannot write arbitrary graph paths, policy fields or the recursion budget.
This is a built boundary, not proof that a revision improved an outcome.
One retained review receipt. 209,825 tokens, three requests, 10,336 ms.
Six levels, from watch-only to bounded automatic. Automatic apply is off by default.
This is a built boundary, not proof that a revision improved an outcome.
Authority and approval Modeled view.
| Platform | Status | Note |
|---|---|---|
| Inside Machine Nerve, DRIVERFORM and STINTFORM | Live |
Physiological signals are context for performance review. They are not diagnoses, emotion detection or fitness-for-duty measures.
Machine Nerve is not a medical device and does not provide clinical diagnosis, treatment, or medical readiness certification.
Private pilot access is reviewed by use case, data sensitivity, and fit with current workstreams.
AI proposals stay inside fixed operations and the authority tier the operator set. AI agreement is never counted as success.
AI review across every product. Proposes exact, versioned changes.
One core and one ontology sit under every product. Each product is one seat on the same record.
See the whole stackOne app for each seat.
The training app. Operators create flows with Eri in Method Studio, and experts write catalogs.
AI review across every product. Proposes exact, versioned changes.
Eri Live
Aligns person and machine on one timeline, runs methods and keeps the record.
Cars, simulators, timing, video and the wearables a driver already has.
Modeled view.
Start from a catalog or create one with Eri. Run your session and review Eri's proposals yourself.
Start a pilot