RovianDevelopment Labs
All work
NHSAmbience AI

Clinical answers that show their working.

NHS Advice & Guidance made every GP query a manual task for a specialist, including simple and repeated questions. Ambience AI drafts a grounded response with page-level citations, ready for a specialist to approve or edit before it reaches the GP.

The specialist review flow on an NHS-blue ground: query, response and review beside a cited clinical answer awaiting approval.

The problem

The NHS Advice & Guidance system let GPs submit clinical questions to specialists, who reviewed and answered them when capacity allowed. Every query entered the same manual queue, whether it involved a complex case or a question the team had answered many times before.

For routine queries, much of the work was finding the relevant guidance and pasting it into a response. The brief was to reduce that repetition without removing clinical oversight: draft a grounded, cited answer for the specialist to approve, edit or replace before the GP saw it.

What we built

A retrieval pipeline over NICE and BSR guidance, wrapped in a clinical workflow rather than a chat window.

  • Answers from the guideline, not from memory. The documents are chunked with their sections and tables intact, retrieved by vector search, and handed to the model as passages; so a numbered reference points at the text that produced the sentence.
  • A refusal instead of a guess. Below the confidence threshold the system declines, and the case still goes to a human.
  • A specialist in front of every answer. They approve, request a revision, or replace it entirely. The GP sees nothing until they act.
The GP consultation list, showing submitted, under-review and closed cases with specialty and urgency labels.
A GP's queue. Every consultation carries a specialty, an urgency and a state — and the state is what decides who is allowed to see the answer.
  1. 01

    GP asks

    Age, sex, specialty and urgency

  2. 02

    Retrieve

    NICE and BSR passages

  3. 03

    Draft answer

    Every claim numbered

  4. 04
    Required gate

    Specialist review

    Approve, revise or replace

  5. 05

    GP sees answer

    Sources attached

The interesting part of a clinical AI product isn't the answer. It's everything that has to be true before anyone is allowed to read it.

Grounding

Every reference carries the guideline title, the page, the section path and the publication date, so a specialist can check a claim in about ten seconds. That is the only reason a human review step is affordable at all.

A specialist’s view of a drafted answer about distinguishing migraine aura from TIA, with two numbered NICE sources listing guideline title, page numbers, section path and publication date.
An answer awaiting review, with its two sources — guideline, page, section, publication date.
The administrator dashboard: total AI responses, share of grounded responses, active consultations and users, with charts by status and specialty and a live RAG event log.
Administrator view. Grounding rate, consultation states, and a live log of what the retrieval pipeline actually did — including how many chunks each answer used.

Details

Context
UCL Industry Exchange Network, with the NHS and Intel
Timeline
24 weeks, October 2025 – March 2026
Frontend
React · TypeScript · Vite · SSE answer streaming with a polling fallback · Recharts · Vitest · Playwright
Backend
FastAPI · PostgreSQL + pgvector · Alembic · JWT auth · Redis queue
Retrieval
PDF extraction · section- and table-aware chunking · cosine vector search · scheduled NICE re-crawl
Inference
Med42 via Ollama, local-first, with a configurable hosted fallback
Delivery
Docker Compose, seven services · nginx TLS · health checks and dependency ordering