AI USE CASES YOU CAN REUSE.English edition · Individuals, independents, small businesses
Spotted on the web

Responding to patients in a health platform by entrusting any medical question to a clinician

Use described publicly by Intercom (fin.ai) — Numan (accessed in November 2026 (undated page)), summarised by the desk. Not tested by iadujour.

The result to aim for

Numan, an online health platform (diagnostics, treatments, accompaniment), has deployed a support agent who answers practical questions and systematically transmits medical questions to the clinical team.

What was done

According to the case study published by Intercom on end.ai, Numan's support was close to 70,000 conversations per month, from delivery follow-up to treatment questions. The company first reworked its knowledge base to ensure that the agent relies on accurate and well structured content. All of the agent's conversations were read manually at the start, before moving on to a 5% monthly audit once confidence had been established. Explicit rules exclude the agent from any clinical subject: any conversation about a drug, a treatment decision or the follow-up of adverse reactions is immediately transmitted to a trained clinician or team member. According to the source, customer satisfaction remained at 90%, and the team focused on complex and clinical exchanges.

Before you start

Tool cited by the source: Fin (Intercom). Gather the information the prompt asks for. Strip confidential data that is not needed and check your tool’s access terms. Features and plans can change.

The method, in three steps.

  1. Gather the context

    Gather the information described in the prompt.

  2. Adapt the prompt

    Copy the prompt below, replace the bracketed items, then paste it into the AI assistant you use. The cited tool (Fin (Intercom)) is not necessarily available to the public..

  3. Reread before using

    Reread the result, correct it if needed and keep the final decision. Caveats are detailed below.

Your starting point.

Replace the bracketed items, then adapt the proposal to your situation. This prompt is written by the iadujour desk It is not a quotation from the source.

The prompt to customise
We deploy a support assistant to a regulated sector:
Here are our application topics:

1. Class each subject: the assistant responded alone / he answers then propose a human / he transfers immediately to a professional.
2. Writes clear transfer rules with examples of triggering sentences.
3. Proposed a quality control plan: complete editing on startup, then sampling.
Don't give yourself any medical, legal or financial advice.

What deserves your attention

In health, the transfer rule to a professional is the most important function of the agent: it is tested before launching and then tested by sample throughout the operation.
Origin of the case. Use described publicly by Intercom (fin.ai) — Numan (accessed in November 2026 (undated page)).
Proof level: Statement by the tool’s publisher. Source checked on 10 November 2026. Use described by the source, not tested by the desk. Original summary written by iadujour.fr: figures and claims are the source’s; the prompt is a desk proposal, not a quotation.
TO GO FURTHER

Other ideas to put to work.

The whole Health theme
Health

Check a patient's contact information before calling the secretary

At Burogest Services (Fernelmont), the voice agent Nora has been in production for about a year: it helps medical secretaries on part of the calls by checking the patient's contact information before transfer.

Tool: Nora (Burogest Services)Type: Spotted
DISCUSSION

Comments.

A field note, a question, a precision on this use case? Comments are reviewed before publication.

Published comments

Loading comments…

    Leave a comment

    Moderation charter. Every comment is reviewed before publication. We refuse hate speech, insulting or discriminatory language, advertising, spam and promotional links, off-topic posts and other people’s personal data.