LangStudy
04 / Internal tooling

Interview a wetland

There is no shipped curriculum. You drop in your own material—reading transcripts, photos of book pages, exam papers—and the system extracts what you don't know yet, writes the lessons, and grades what you produce.

Ingest anything

Raw context in, curriculum out

An LLM-in-the-loop cycle reads your material against your current level per skill, then writes lessons, drills, and cards where the gaps actually are. A graded lexical corpus double-checks the classifier.

Voice both ways

Speaking and listening are first-class

ElevenLabs voices generate dictation and shadowing audio; your recorded speech is transcribed and scored word-by-word against the target. A separate judge model reviews free production—and you can override it.

Sessions that end

No streak, no flame, no nag

Spaced repetition with a retention dial, a capped new-card budget, and an honest "you're caught up" ending. Progress is quiet data—a due forecast and mature-word counts, not gamification.

Session · Oral12 of 19

Répétez :« Les mécanismes de financement doivent être vérifiables. »

Last attempt: 96% word accuracy · 2 items queued for review
Observe your material Orient against your level Decide what you need Act: new lessons repeat

Language study is the simplest thing Anima does, simulating live conversations at a user's chosen level.