A learner
A learning platform built around how studying actually goes, not how a syllabus says it should. That is who we build for.
Anyone can wire up a model. The hard part is the hour after somebody opens your app for the first time: whether they can find the thing they came for, whether they understand what just happened, and whether they come back tomorrow. That is the part we work on.
None of this is new — most of it is older than the web. It is just rarely done all the way through, so here is what each one costs us.
A person should never have to wonder whether the thing they just pressed is working, finished, or broken.
In our apps Every control in our apps answers within a second — with the result, a spinner, or an error. A click that does nothing visible is filed as a bug, not as a slow page.
Screens should speak the language of the person using them, not the language of the database behind them.
In our apps No internal codes on a user-facing screen, and no error that only makes sense if you have read the source. If a sentence needs a glossary, it gets rewritten.
People explore software by pressing things. That should be safe, and the way out should be obvious.
In our apps Cheap actions get an undo rather than an "are you sure?". The expensive and irreversible ones — and only those — get the confirmation.
The best error message is the one that never had to be written, because the interface would not let the mistake happen.
In our apps Dates come from a picker, amounts are bounded, and lists are chosen from rather than typed. Where something still goes wrong, the message sits next to the field that caused it and says what to do next.
Nobody should have to hold what they picked two screens ago in their head to finish what they are doing.
In our apps Choices stay visible while they still matter, and every step of a long form can be looked back at without losing what has been typed.
A better-but-different control is usually worse. Familiar beats clever nearly every time.
In our apps One button, one date field, one way to pick a person — shared across our apps, so learning one of them is most of the work of learning the next.
Keyboard, screen reader, big text, poor contrast, one hand, bad light, slow connection. All of it is normal use.
In our apps Every input has a real label, every dialog takes and returns focus, and colour is never the only thing carrying a meaning.
A confident wrong answer is worse than no answer. People need to know what the machine did and how to overrule it.
In our apps Anything generated is labelled as generated, is editable before it counts, and never quietly becomes a decision on somebody’s behalf.
Opinions about interfaces are cheap and everybody has one, ours included. This is the loop we run instead.
We sit with people while they use the thing. Five sessions finds most of what is wrong, and it finds it before anyone has argued about it in a meeting.
A written prediction: what we think is going wrong, what we will change, and the number that should move if we are right. Written down first, so we cannot decide afterwards what we meant.
The narrowest change that could test the guess, in front of real users within days. A change that takes a quarter to ship is a change nobody will ever be able to attribute anything to.
Against the number we named in step two, not one chosen afterwards because it looks better. Flat is a result. Worse is a result we publish internally rather than quietly roll back.
Most ideas do not survive this, including ours. What is left is the part of the product that has actually earned its place on the screen.
The technology
The usual way to put AI in an app is a text box in front of a very large model that arrives knowing nothing about you. We build the other way round: many small interactions, each already holding who you are, what screen you are on and what you are in the middle of — so what comes back fits the work instead of describing it.
$19
a month for a whole practice on Practiceful, everything included, plus $7 per extra provider
$29
a month is where Yoshuko starts, through $79 and $199 — with a platform fee of 5%, 3% or 2% on what a creator sells, collected by Stripe
5
usability sessions is where we start — not a survey, not a focus group, not our own opinion
0
screens ship without an empty state, a loading state and an error state, because those are what people actually meet first
Two apps, both in public alpha, both free to try.
Tell us about it. A person who builds these apps will write back.
