AI triage assistant deployed across 38 clinics
Cut intake time by 41% with HIPAA-compliant LLM workflows.
- AI / ML
- Custom Software
- QA
- Python
- Anthropic
- FastAPI
- Pinecone
- AWS
January 28, 2026
The starting point
Helix Health's intake process was paper-heavy and inconsistent across clinics. Wait times were the #1 patient complaint.
Earlier LLM pilots had stalled on HIPAA review — no evals, no eval harness, no story for hallucination control.
How we worked
We built an eval-first triage assistant: every intent classification was scored against a clinician-labeled gold set before any feature shipped.
PHI never left the VPC — retrieval and inference run on AWS with private endpoints and explicit logging.
The first launch was shadow-only: the assistant ran in parallel with human intake for six weeks, with weekly clinical reviews.
What changed
Intake time dropped from an average of 14 minutes to 8 minutes — without a single PHI incident.
Patient NPS lifted 18 points across the 38 pilot clinics.
Helix's clinical team now owns the eval harness, with new evals added weekly.
More from the same shelf
Cross-border payments at sub-second settlement
Re-architected ledger and reduced settlement time by 92%.
Real-time fleet visibility for 12,000 vehicles
Replaced legacy SAP layer with a modern event-driven core.
From design tool to platform — onboarding rebuilt in 8 weeks
Doubled activation rate without growing headcount.
Have a similar project?
We've shipped this kind of work before — let's talk about how the lessons apply to yours.
Posted 2026-01-28 by Official Byte. Read more on case studies.