Meet the coach

Ask the coach — about the coach.

This is the AI coach that works with teachers in their daily check-in, answering for itself: how it coaches, what research shaped it, and who can see what. It's an AI, and it won't pretend otherwise — no salesperson in between.

The coach, on itself An AI, plainly disclosed · Nothing you type here is saved

Ask me how I work — the research behind me, what your teachers' words are protected by, or why I never say "great job."

This conversation lives in this browser tab and nowhere else. The coach here talks about itself — real coaching happens inside a private check-in with a privacy floor a public page can't have.

A few of the findings it's built on

Every design decision in the coach traces to a named finding. Four of the load-bearing ones — and what we built because of each:

Recording progress toward a goal, and reporting it to someone, measurably raises goal attainment.

Meta-analysis of 138 randomized trials (19,951 participants), Psychological Bulletin

What we built because of itThe daily check-in is exactly that shape: one goal, progress in writing, reported to a coach — minutes a day.

Over a third of feedback interventions make performance worse. The dividing line: feedback aimed at the practice helps; feedback aimed at the person — including praise — backfires.

Meta-analysis of 607 effect sizes, Psychological Bulletin

What we built because of itThe coach never grades, scores, or praises the person. It talks about what the teacher tried and what happened.

AI that flatters measurably degrades people's judgment — while raising their satisfaction with it.

Controlled experiments, Science, 2025

What we built because of itThe coach is free to not affirm, and teacher-satisfaction ratings are never used to tune it. Ever.

Teacher coaching is among the most effective PD forms ever measured — and more coaching hours did not mean better outcomes. Specificity beats dosage.

Meta-analysis of 60 causal studies of human coaches, Review of Educational Research (they studied human coaches — the AI trials support goal attainment, and that's the only claim we make)

What we built because of itOne specific practice goal per 30-day cycle, minutes a day — not hour-long sessions, and no inflated promises.

School leaders get the full evidence page — every finding, every named study, and what we deliberately don't claim — inside the platform dashboard.

The rest is better felt than described

The walkthrough shows a teacher's day with fictional data. The 30-day trial is the real thing — full access, no card.

See what teachers see → Try it free for 30 days →