Clinical Communication Course · practice tool
Here are your simulated consultations. You can interact with the patients, try new things, and be provided with detailed feedback at the end of your consultation.
Once the consultation starts, try to reply conversationally, at the pace you normally would.
Each level focuses on a different part of the encounter. The capstone brings them together and removes the supports.
Optional. Nobody sees this but you. Choose a difficult one if it gives you something useful to practise.
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 but never scored. Set it to your real clinic slot if the time constraint helps, or turn it off and focus on the skill first.
Each patient has their own voice. Select the tick box above to enable this option.
There are three ways you can do this:
They will all type text into the same box. Each option may send your audio outside of your computer to whoever provides them, so if you'd prefer that not happen, you can just use the text by typing instead.
When you are finished with your response, click the send button.
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. This lets you edit and version the content without touching the code. The tool stamps the active pack onto every record, so any change during a cohort remains visible in the data.
Study export. One file containing consent, participant ID, tool and content versions, every encounter, and the engagement record.
Before you start
Reliability bench
For the reliability study that needs to happen before the scores mean anything. Read the transcript, score it against the anchors, commit your scores, then see what the model gave it.
Module 5 · reactions to uncertainty
Four weeks on · finishing the course
End of module
Knowledge check
Your record
This is compared only with your own earlier work. There are no points and no leaderboard.
Your day
Here is your calendar and the brief notes you have about this new booking.
Before you go in
Straight after
Before you start
Predict your score before you see the assessment. The gap between the two is useful information.
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
Rate each one, from not yet to strong, the way you think an assessor would. Then we show you the assessment.