All work

Demo build

Front-desk assistant for a multi-speciality clinic

A demo build for a fictional client. It shows how we would scope and build this system; it is not a paid client project.

The problem

Reception staff spend much of the day answering the same questions about timings, doctors, test preparation and prices, while calls after hours go unanswered.

What we built

A WhatsApp and website assistant that answers from the clinic's own timings, doctor rosters, lab FAQs and price lists, cites its sources, and hands the chat to reception for anything medical or unclear.

How it works

  1. Clinic documents are split into passages and indexed with embeddings in a vector database
  2. Each question retrieves the best-matching passages and the model answers only from them
  3. Answers include links to the source; low-confidence questions go to a human
  4. Reception sees every conversation in one dashboard and can take over

What it changes

  • After-hours questions answered instead of missed
  • Reception time freed for patients in the building
  • Medical questions always routed to a person

Watch it run

The same system, step by step.

A patient asks the clinic a question at 11pm

A knowledge assistant searches the clinic's own documents and replies with an answer it can point to.

Step 1 of 5

Message received on WhatsApp at 23:04

Tell us about the work that eats your week

Book a free 30-minute discovery call. You'll leave with an honest view of whether AI can help, and what we'd build first.

Or email [email protected]