HEALTHTECH · 7 mo · live · 52% time saved per clinician/week

Ambient scribing for ambulatory care.

RAG-grounded scribe agents that generate clinician-ready notes from ambient audio with source-linked citations.

Used with permission · Anonymized

4.2s
Note draft latency
99.2%
Source-citation rate
6.5h/week
Time saved per clinician
94%
Clinician sign-off rate

The problem

Documentation burden is the single biggest driver of clinician burnout. Existing scribing tools generated text — but not the structured note clinicians could sign. Citations to the source utterance were essentially nonexistent.

Our approach

We built a scribe pipeline with two non-negotiable invariants:

  1. Every claim has a source. The clinician can hover any sentence and see the ambient transcript span that produced it.
  2. Templates are owned by the clinical team. Note structure (SOAP, narrative, etc.) is defined per-specialty in the CMS; the agent fills the slots.
The first version we shipped had a 12% citation-failure rate. The third had 0.8%. The evals caught every regression.Eng lead, Healthtech, US

The architecture

02 · Reference architecture

What we actually ship.

Every system we build follows this shape. Client at the edge, tools in a sandbox, traces everywhere, evaluators gating output. No black boxes, no "it works on my machine."

EDGE
Client
web · mobile · API
Gateway
auth · rate-limit · PII redact
ORCHESTRATION
Orchestrator
planner · router · memory
Durable · exactly-once
AGENTS & TOOLS
Retrieval
hybrid · rerank · cite
Tool calls
sandboxed · timeboxed
Evaluator
gates · rubrics · LLM-judge
DATA & TRUST
Vector + BM25
tenant-isolated
Traces / logs
OTel · replayable
Signed output
auditable · rollback

A run, on this system

04 · Run

Watch an agent do the job.

Three real production scenarios, replayed at observed latency. Every box is a span; every span has tokens, cost, and an eval gate. This is what shows up in your traces, not a marketing animation.

POST/api/v1/agent/run7-minute ambient consult → clinician-ready note with source-linked citations.
trace · clinicalspan_id 7c1f…
orchestrator.run0ms
PLANorchestrator.planorchestrator · 80ms · 178 tok · $0.0013
Plan rationale

Scribe pipeline: ASR with medical lexicon, retrieve patient context + template, draft per-SOAP-section, evaluator gates clinical-safety claims.

Subtasks
tool.asrretrieval.contextreasonerevaluator
0ms/3.07s
LATENCY0msbudget 3.00s
TOKENS0in + out
COST$0.0000budget $0.025
EVAL GATEdeterministic + LLM-judge
READY · clinician review
SOAP note drafted. 14 citations resolved. 2 low-confidence claims surfaced for clinician.
latency3.12scost$0.022tokens3,104evals9/9

Outcomes

0.0h
Time saved / clinician / week
0.0%
Citation-failure rate
0%
Clinician sign-off rate
START

Ship the first system.

Fixed-price discovery in 2 weeks. You leave with an architecture, a working spike, and a build plan.