02Healthcare
Triage assistant for an outpatient network
Voice + chat intake that routes patients in under 90 seconds and books the right specialist on the first try.
90savg. triage
Client
Multi-specialty outpatient network · 12 clinics · NCR
Engagement
8 weeks · Premium engagement
Stack
Twilio Voice · Whisper · GPT-4o · FHIR APIs · Zoho Bookings
01The Challenge
What we walked into
Front-desk staff spent the first 4-6 minutes of every call collecting symptoms, history, and insurance details — and still mis-routed roughly one in five patients to the wrong specialist, causing reschedules and bad reviews.
02The Approach
How we tackled it
- 01Built a voice + chat triage agent that asks the right follow-up questions based on the symptoms shared, in English and Hindi.
- 02Integrated with the existing FHIR record system so prior history is folded into the routing decision automatically.
- 03Routed booked appointments straight into Zoho with the right specialist, room, and prep notes attached.
03The Outcome
What changed
- Average triage time dropped from 4m20s to 1m30s.
- First-try specialist match improved from 79% to 96%.
- Front-desk staff reallocated to in-person check-in, cutting wait times by a third.
“
Patients tell us check-in feels calmer now. That's the metric that actually mattered to us — and the one we couldn't have measured before.
Have a similar problem?
Let's build something worth using.
Tell us about the bottleneck. We'll come back with a free 30-minute call and a quick read on what's feasible.
Start a conversation→More work
View all →Retail
Inventory copilot for a 30-store chain
Replaced manual stock checks with a forecasting agent that cut out-of-stocks by 38% in one quarter.
−38%
stock-outs
Logistics
Document automation for cross-border shipping
OCR + LLM pipeline that ingests bills of lading, flags discrepancies and clears paperwork without an analyst in the loop.
6×
faster clearance