AI phone assistant for dermatology practices
The waiting list is most of the phone. Tel-Agent answers the calls about it and pulls out the few that should not be waiting at all.
- Waiting list
- Skin check or acute
- Referral
Why a dermatology practice phone is mostly one question
A dermatology practice's calls are dominated by people asking when they can be seen, because the answer is usually months away. Answering that two hundred times a week is a full-time job that produces no appointments - and buried in it are the few calls that should not be on the waiting list at all.
How the AI receptionist handles a dermatology enquiry
It answers and asks whether this is a routine check or something acute.
It takes how long it has been there and whether it has changed.
It asks about a referral, and whether the caller is insured or private - in DACH that often decides the waiting time itself.
Anything matching the practice's acute wording is transferred to a person immediately.
It asks the question nobody has time to ask two hundred times: would you take a slot at short notice.
What the agent is told to ask
Written by you, in your own words, as the assistant’s instructions.
What a dermatology phone assistant should and should not decide
What it does
- Answers the waiting-list calls that fill the day
- Records the description and the duration in the caller's words
- Applies the practice's own acute-wording transfer rules
- Builds a short-notice list that makes cancellations refillable
- Keeps recordings on the practice's own server
What it never does
- Judge whether a skin problem is urgent
- Suggest what a mark or a rash might be
- Promise a waiting-list position or a date
- Advise on creams, treatments or sun exposure
- Store an image or a description off the practice's machine
Questions
Can it tell an urgent skin problem from a routine one?
No, and it should not. It records the words the caller used and how long it has been there, then applies the practice's own transfer rules. A practice can decide that certain descriptions always reach a person; the model does not get to make that call.
Does it help with the waiting list?
Mostly by asking one question nobody has time to ask two hundred times: would you take a slot at short notice. That answer is what makes a cancellation refillable.
How long is the wait at a dermatology practice?
That is the question the phone is mostly asking, and only the practice can answer it. What the assistant changes is that nobody has to answer it two hundred times a week by hand - the enquiry is recorded with its date, and the short-notice question is asked while the caller is still on the line.
Can it recognise something that should not wait?
It applies wording the practice supplies, not judgement of its own. A practice can decide that certain descriptions - a mole that has changed, a spreading rash, anything with bleeding - always reach a person, and those rules run before the model does.
Does it deal with cosmetic enquiries differently?
It can. Cosmetic and medical enquiries usually go to different lists, different waiting times and sometimes different practitioners, so the question is worth asking on the first call rather than discovering it later.
What happens to the description a caller gives?
It is recorded in their own words and kept on the practice's own machine. A description of a skin condition is health data under Article 9 of the GDPR, which is the case for self-hosting rather than a hosted voice product.
Does the EU AI Act allow an AI to answer a waiting-list call?
Yes, under Article 50 of Regulation 2024/1689, which asks that the caller be told they are speaking to a machine - that line belongs in the greeting you configure. Annex III names emergency healthcare triage, so anything that ranked callers by how ill they sound would be a high-risk system. The distinction the Act draws is between assisting and deciding, and this agent assists: it never judges how urgent a symptom is. Austria's KI-Servicestelle at RTR publishes the same reading of the transparency duty.
Who is the data controller for what a caller to a dermatology clinic says on the phone?
You are. A waiting-list call is health data, which Article 9 treats as a special category, and Tel-Agent is self-hosted with your own model keys, so the recording, the transcript and the record it writes stay on your server and never reach Dpro GmbH. There is no processor agreement to sign with us because we never receive the data, and the source is AGPL-3.0, so you can check that rather than take our word for it.
Can a dermatology clinic run this in the United States?
There is no single federal AI statute to comply with, but a phone line carries older rules. A US practice is under HIPAA, and HIPAA is where self-hosting pays: there is no business associate agreement to sign with us, because no call reaches us. Consent to record is set state by state, and California and Illinois among others want every party to agree. Running the software yourself makes you the caller of record, so the disclosure and the recording switch are yours to set.
Not usable yet. The day it answers a real call will be a release, not a newsletter.
Watch the repository