Your program material. Interactive practice. Evidence of competency.
Upload the material your program already teaches from. Students practise against it with an AI tutor that cites your documents and declines to answer what they do not cover.
Rendered by the product, not a screenshot
One task, start to finish
This is what a learner does here.
Not a tour of a dashboard. One piece of practice from this program, played through — the same interaction an enrolled student gets.
Working today
What this program gets on day one.
Every capability below is running in a real signed-in session and gated before it ships. Not a roadmap.
Interactive anatomy diagrams with tap-to-reveal labelling for active recall
Six anatomy diagrams ship today, each one a labelling task the learner completes rather than a picture to look at.
Answers cited back to your own material, with the instructor one tap away when the material does not cover it
On our go/no-go benchmark every answer retrieved the right passage, carried a valid citation and stayed inside the material, and every out-of-scope question routed the learner to the instructor rather than a guess — against 54.2% for handing the model the whole document.
Instructors attach their own documents to a course, review them as a draft, and publish when ready
Fourteen checks driven through a real browser, including that a student cannot see a draft and that publishing opens the document itself.
Preview exactly what an enrolled student sees before you release anything
The preview is built from the same rule the database itself enforces, so it cannot drift from what a student actually sees.
See which learners are struggling and which concepts they are stuck on
Twenty-nine automated checks on the cohort report, plus five more driven through a real browser.
Talk to the tutor out loud, interrupt it, and be understood
The realtime voice loop ships today and is exercised before every release.
Competency is scored by rules against an approved rubric, not by a language model’s opinion
Forty-one automated checks, including a deliberate break to prove the checks can fail. The model records what it observed; the rubric decides the mark.
Every procedure step and rubric criterion carries a reference back to the document it came from
A criterion with no source reference is refused before it can be saved. Not a warning — a rejection.
A glimpse of what Ava draws, live
Concepts they can take apart.
Every figure here is rendered by the same code path that runs for a real student. Not screenshots. Not stock illustrations. Drag one, and it moves.
Who this is for
Programs already running this material.
One engine, other workforces