Context
Our client runs an obesity care programme built around semaglutide treatment. Patients on that pathway have questions constantly — about dosing, side effects, what to expect, what is normal — and most of those questions arrive outside clinic hours.
Problem
Two things make a healthcare assistant harder than a support chatbot.
The first is that the cost of a wrong answer is not a bad review. A general-purpose model asked about medication dosing will answer confidently whether or not it should, and in this domain confident and wrong is the failure mode that matters.
The second is that the useful answers are specific to this programme — its protocol, its escalation rules, its patient journey — not to obesity treatment in general. A model relying on its training data would give plausible, generic, unusable answers.
So the design problem was a narrow one: be genuinely helpful within the programme’s boundaries, and reliably decline or escalate outside them.
Approach
The design followed from the two constraints above.
Ground the assistant in the programme’s own material. Answers are drawn from the client’s protocol and patient-journey content rather than the model’s general knowledge of obesity treatment, so that what a patient reads matches what their programme actually tells them.
Draw the boundary explicitly, and escalate across it. The harder half of a healthcare assistant is not answering well — it is recognising the questions it must not answer. Clinical judgement, dosing decisions and anything outside the programme’s scope route to a human rather than being handled confidently and wrongly.
What we built
A conversational AI assistant supporting patient engagement and guided assistance across the obesity care journey.
Outcome
The assistant supports patients across the care journey, including outside clinic hours, within a scope the client defined.
Volume and resolution figures for this engagement are not published.
Related
Retrieval-Augmented Generation for an Education Platform · Healthcare Management CRM · AI Engineering
