Chatbot and RAG · cost efficiency · HIPAA
Member messaging,
6x patients → 1.9x team
The mandate: as patients grew 2x to 4x, medical team headcount costs could not grow with them. I led the AI engineering to meet it. Patients grew 6x, the medical team grew 1.9x, and this assistant is a core part of that work.
The problem
More patients meant more messages. The company set a cost efficiency mandate: patients could grow 2x to 4x, but medical team headcount costs could not grow at the same rate.
What I built
A HIPAA compliant patient support chatbot on OpenAI GPT-4.1, GPT-5 mini and GPT-5.4, with retrieval over 100+ clinical and company protocols stored in Postgres. The protocols were customized by insurance company, so the answer had to depend on whose plan the patient was on.
How it was checked
Evals in Langfuse, with LLM as judge used to build the golden data set and to check prompt changes.
Result
The assistant answered two thirds of all patient messages on its own, while message volume grew 8x. Patients grew 6x against a medical team that grew 1.9x, so each clinician covered 3.2x the patients. The mandate was 2x to 4x.