Work in progress, round 7 of the council loop. Scores, captures and code are still changing; this page is redeployed at the same address as rounds land.

Prototype · ONC2-8580 · staging data and staging QA accounts only · not shipped · api 7928fbbe, app beabfe143

The tutor invites you in, on Home

When a learner opens Home, their course's tutor (Rezzy for the medical courses, Savvy for CFA and CPA, Casey for LSAT and the Bar) opens with one short message about what the learner did last, and one or two things it can do about it right now: a quiz on the exact questions they missed, their due cards, the lesson they should read next, or a question they can answer with a tap. Each tap lands where it says: a quiz already built, a screen, or a chat that starts from the card.

Code decides what is possible and true; one model call decides what is worth saying today and says it in the tutor's voice; code checks the result before the learner sees it.

How it works, end to end

1. Snapshot. SQL reads only the active course (and its selected exams): recent sets and their misses, lessons read, due and forgotten cards, readiness trends, exam date, rhythm, onboarding and the tutor's memory notes.
2. Offers. Code turns the snapshot into things the app can run today, each with real ids and one count used by its label, its facts and its target.
3. Compose. One structured call (Gemini 3.5 Flash Lite) picks one or two offers and writes the message, buttons, chips and at most one block.
4. Validate. Every id is an offer; every number belongs to an offer the card uses; no other course's exam or tutor; the rules the model breaks most. A failure retries once with fixes, then falls back to a card built from the rules.
5. Cache. Stored per learner, course and exam scope with a fingerprint of the data; an unchanged learner gets the stored card in ~0.1 s.
6. Act. A tap goes to the server, which resolves the offer on the stored card (a quiz template from the exact question ids, a route, or a chat whose first bubble is the stored message and whose first turn follows the offer's plan).

Component catalog

The model picks components by reference; the app draws them from design-system parts. It can't put a number or an id in one.

Action registry

Latency and cost

Eval v5 at api 7928fbbe: 36 synthetic learners across the nine courses (the situations each course meets: misses, a lesson read, due cards, an exam passed, a walkthrough left part way, a new learner), one Gemini 3.5 Flash Lite compose each through the api's provider setup, one retry with the validator's errors, then the rules' card. A second model (Gemini 3.6 Flash) judges each valid card.

• Valid on the first call: 27 of 36 (75%). After one retry: 35 of 36. Fallback to the rules' card: 1 of 36 (3%), the LSAT "how did the exam go?" card.
• Latency: first call p50 1.45 s, p95 2.0 s; whole compose with its retry p50 1.6 s, p95 3.3 s, max 4.2 s.
• Cost per compose: $0.00122 mean, retries included (about 2,860 tokens in, 165 out).
• Output judge: 34 of 35 valid cards pass all four checks (person, times, claims, fit); voice 4.4 of 5.

On staging, a cold open composes inline in 1.5-5 s; a stored card returns in about 0.1-0.2 s. At one fresh card per active learner per day, 10,000 learners cost about $12 a day.

Gallery: tutors, courses and states

Indian Medical PG (NEET-PG) Rezzy

Learner state: a PYQ set yesterday, 9 misses across two subjects

You had 9 misses in yesterday's PYQ set, 7 of them in Internal Medicine. Want to walk through them?

Walk me throughTry the 9 again

Something else

block: question_set · source: composed

US Medical PG (USMLE) Rezzy

Learner state: read a lesson today, no questions on it since

You have 40 unreviewed flashcards in Antimicrobials waiting for you. Want to review them now?

Review all 40

Something else

block: none · source: composed

UK Medical PG (UKMLA) Rezzy

Learner state: exam month set months ago, back after a break

Still aiming for December?

Try 10 questions

Same planNew exam date

block: question_set · source: composed

NCLEX-RN Rezzy

Learner state: a quiz four days ago, 3 misses; prefers flashcards

You missed 2 in Medication Administration Fundamentals and 1 in Mobility, Body Mechanics & Positioning 4 days ago. Want to walk through them?

Walk me throughTry the 3 again

Something else

block: question_set · source: composed

MCAT Rezzy

Learner state: exam date has just passed

Your MCAT test date was 5 days ago. How did it go?

Went wellNot sureNot greatDidn't take it

block: none · source: composed

CFA Savvy

Learner state: a quiz three days ago, misses in Fixed Income

Fixed Income is where it slipped, with misses spread over 5 topics when you did the quiz 3 days ago. Let's work through them.

Walk me throughTry the 5 again

Something else

block: question_set · source: composed

CPA Savvy

Learner state: a weak set yesterday, 7 misses

Of your 7 misses in Assessing Risk and Developing a Planned Response yesterday, 2 were in Materiality. Let's walk through them or try them again.

Walk me throughTry the 7 again

Something else

block: question_set · source: composed

LSAT Casey

Learner state: new, told the tutor about a worry (pacing)

You mentioned running out of time on timed sections, so let's go at your own pace with Strengthening, weakening, and explaining: reasoning before speed. Start there, or talk it through first?

Try 5 to start

Talk it throughPlan my week

block: question_set · source: composed

Bar Exam Casey

Learner state: retaker, misses in Contracts two days ago

You missed 4 in Contracts 2 days ago across formation, content, defenses, and performance. Let's walk through them.

Walk me throughTry the 4 again

Something else

block: question_set · source: composed

Tap-throughs

Recordings come with the final version of this page.

Real and mocked

Real: snapshot from staging data, offers with real ids, the model call through the api's provider setup, validation, fallback, caching, the act endpoint (test templates, flashcard ids, routes), the seeded chat with server-side turn instructions, analytics events. Seeded: the staging QA learners' history (wrong answers, lessons read, due cards, exam dates, memories) written by a staging-only script; flashcards are the course's own cards or built from the course's own plain MCQs, never another learner's. Not built: the Trigger.dev precompute (designed, not deployed), a persisted events table (Redis + PostHog only), games filtered by topic (games open on a subject where they can).

Known, outside this prototype

• The exam date, pain points and study tools are read from the learner's profile, not per course, as exam pace and the week plan read them. A learner who switches courses keeps the first course's exam date until they change it. Everything else in the snapshot is limited to the active course (tested in invite.snapshot.unit.test.ts).
• Days away and the streak count activity in any course: they describe the learner's rhythm, not course content.
• Template quizzes have no timer, so no offer is timed (the exam-instinct offer is a plain quiz until the player has one).
• Home's exam pill rounds an estimate to the nearest month ("About 1 month to go" at 20 days); the card no longer has its own countdown, and says only months for an estimate.
• The review player shows a cloze card's raw braces; the card's peek blanks them.
• The chat shows its Thinking trace and the voice teaser over a seeded chat, and dev builds show toasts over captures.
• The first turn of "Make 10 cards" took about 28 s on staging (the model writes ten cards before saving them); the walkthrough's first turn is about 8 s. Streaming the cards one at a time is the fix, outside this prototype.
• The api exits on an uncaught error from a chat message with a non-UUID id (an adjacent bug, reported separately).
• Past chats are polled while a reply streams.
• Analytics set nav: "approach_b" literally, like the rest of approach-B Home; the card renders only there.
• A topic quiz trusts the bank's topic tags. On staging some are loose: US Medical PG's Pharmacology "Antimicrobials" holds 373 questions, including an alprazolam question and a fracture case, so a quiz on it can open off topic (prod not checked).

Open questions

• Topic and lesson names are grounded by the prompt only; should the validator check every named topic against the snapshot?
• Precompute on events (a set submitted, the day rolling over) in Trigger.dev so the first open is never inline?
• A timer for template quizzes, so an exam-instinct offer can be timed.
• Where the card's taps and ignores should live long term (Redis and PostHog today, no table).
• Whether to let the card replace the day's prompts for own-schedule learners, or always sit above them.
• How often a learner should see a check-in (exam went, feeling) before it reads as nagging.
• The exam date and pain points live on the profile, not the course: should a course switch ask for the new exam date (exam pace and the week plan share this)?
• Should the eval judge run on a sample of live cards too (about $0.0009 a card), feeding failures back into the golden set?

Council score history

Two councils (Claude Opus 5.5 and GPT-6.1-Sol), each with learner reviewers for a Rezzy, a Savvy and a Casey course and an engineering reviewer, fresh every round. The bar is 9/10 on both axes from both councils. Round 7 is in progress.