Clinical Communication Course · practice tool
One simulated consultation. You talk, they answer, nobody coaches you while it is happening unless the level says so. Afterwards you get your own sentences back, with what each one did.
Each level turns on a different part of the encounter. The capstone turns everything on and takes the supports away.
Optional. Nobody sees this but you. Picking a hard one and missing it teaches you more than not picking one.
Kept in this browser only (localStorage), never sent anywhere except the Anthropic API. For a cohort, deploy the included proxy instead and leave this blank.
Length is recorded either way but never scored. Set it to your real clinic slot if you want the constraint, or turn it off if you would rather work on the skill first.
Off by default, because the stock voices sound synthetic and a bad voice is worse than none. On a Mac, System Settings, Accessibility, Spoken Content, System Voice, Manage Voices, then download an Australian or British Premium or Enhanced voice. They are free, they are a large improvement, and they appear in this list once installed.
Your voice in works three ways: the mic button below the text box, your operating system's dictation, or Wispr. They all type into the same box.
Load a .json exported from a previous encounter and see its debrief again.
Nothing is sent anywhere and no key is needed. This is also how a second human marker reads a transcript
alongside the scores it was given.
Mark one blind instead. For the reliability study: you score the transcript against the anchors without seeing what the model gave it, then compare and export the pair as CSV.
Content pack. The patients, levels, anchors and questionnaire items can all be replaced with a JSON file, so content can be edited and versioned without touching the code. Whichever pack is loaded is stamped onto every record, so a change partway through a cohort is visible in the data rather than invisible.
Study export. One file with everything: consent, participant ID, tool and content versions, every encounter, and the engagement record. This is the file a study team asks for.
Study
Reliability bench
For the study that has to happen before any score means anything. Read the transcript, score it against the anchors, commit, and only then see what the model gave it.
Your record
Nothing here is compared to anyone else. There are no points and there is no leaderboard, because the thing worth getting better at is not a thing you can win.
Your day
This is the whole file until they walk in, and it is about as much as you normally get.
Before you go in
Two questions, and they are about you rather than about them. An assumption you cannot see is one you cannot examine, so this gets written down now and handed back to you afterwards.
Straight after
Do this while it is still warm. It takes about a minute and it is the part that changes what you do next time, more reliably than the score does.
Before you start
Predict your own score first. The gap between what you predict and what you get is a measure in its own right, and it usually shrinks faster than the score does.
Elapsed
In play this level
Support
Every hint you take is recorded. That is fine, it is the point of a scaffold.
Escape hatch
The encounter is also saved to this browser after every turn, so a crash or a reload does not lose it.
Before you see the score
Score each one 0 to 3 the way you think an assessor would. Then we show you the assessment.