NewNew: The enterprise guide to Agentic AI — 24 min read.

Read →
Case study · Healthcare Providers · Conversational AI

41% reduction in scheduling abandonment at a children's hospital — bilingual conversational AI

A children's hospital was losing 34% of scheduling calls to abandonment during peak hours and had no way to serve Spanish-speaking parents after hours. pronix.ai deployed a bilingual conversational scheduling agent integrated with Epic MyChart — abandonment down 41% and booking cycle at 3.2 minutes.

Client
Regional children's hospital, 28 clinics
Industry
Healthcare Providers
Platform
Amazon Connect · AWS Bedrock · Epic MyChart
By pronix.ai CX Engineering6 min readQ4 2025
-41%
Scheduling abandonment
3.2 min
Average booking cycle
58%
Spanish-language self-service adoption
0
Clinical safety mis-routes

*Representative outcome; results vary by client, scope and platform configuration.

The challenge

Peak-hour call abandonment averaged 34%, and 22% of the patient population spoke Spanish as their primary language with no self-service parity. Every missed call was a missed visit.

Our approach

Step 01

Bilingual from day one

English and Spanish trained equally — not a translation layer — with pediatric intent coverage across well-visits, sick visits, referrals and rescheduling.

Step 02

Epic MyChart writeback

Bookings landed directly in Epic with the right template, provider and location — no callback queue.

Step 03

Guardian consent handling

COPPA-aware consent capture for anyone under 13 — routed guardian-first with age-appropriate authentication.

Step 04

Clinical safety triage

Symptom-triggered urgency routing — anything red-flag went to a nurse line inside 30 seconds.

Step 05

Access team dashboard

Real-time view of intent mix, hand-off reasons and containment — access leaders could tune the agent instead of the IVR menu.

For Chief Patient Access OfficerFor CMIOFor COO

Illustrative case study. Scenarios, metrics, quotes and client details are representative composites based on Pronix engagements and industry benchmarks unless a named client is shown with written consent. Outcomes vary by client, scope, data quality and platform configuration. Nothing on this page is a guarantee, warranty or professional advice. See our Terms of Use for the full disclaimer.

Trademarks.

AWS, Salesforce, Microsoft, NICE, Genesys, Kore.ai, Google, ServiceNow, Amazon Connect and logos referenced on this site are trademarks of their respective owners. References are for descriptive purposes only and do not imply endorsement, sponsorship or partnership beyond stated partner relationships. See our Disclosures.

Bring this to your program

Talk to the team that shipped it.

Book a working session with a pronix.ai lead on this practice — we'll map the approach to your platform, industry and constraints.