Questions, answered.

It goes further than that. The persona model is built on the expert’s own teaching, the retrieval is grounded in their corpus and scoped to them, and the voice is a clone of theirs. So the corrections, examples and progressions you receive are the ones they would give, and the voice that delivers them is theirs rather than a generic narrator on a generic model.

Their method is encoded in a system prompt that runs on the server, and the retrieval only ever reaches material filtered by their expert id, so the model cannot wander into another teacher’s content. There is also an in-character refuse-list and an output filter that keep it on topic and stop it from leaking its instructions, even when someone asks for them directly, and those guardrails are unit tested.

It is built for advanced learners, roughly B2 and above, who want depth instead of gamification. That tends to be professionals refining nuance, preparing for IELTS, or sharpening business communication. If you have outgrown the mass-market apps but a private coach is hard to sustain, this is the gap it fills.

Time to mastery on a standardized post-test, compared against a linear course taught by the same expert. The target is a reduction of at least half, and the system is instrumented per skill so the number is something we can actually read rather than a slogan. We track it because it is the honest test of whether the adaptation is doing real work.

Yes, on the higher tiers. Inner Circle at $399 a month includes a monthly one-on-one with the teacher, and Practice at $199 includes two live group sessions a month. The Method tier at $99 is the digital memory on its own, with no live time, which is why it costs less.

Yes. There is a seven-day free trial with no card required to start, and you can cancel in a couple of clicks from the dashboard. You can also pause your subscription for one to three months without losing your progress, so a busy stretch does not cost you your place.

No. Your conversations stay private to your account, and we do not sell your data or train third-party models on your sessions. We do use aggregated and anonymized telemetry, such as where learners commonly trip, to improve the routing and the engine, since that is what makes each cohort move faster than the last.