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

Read →
Healthcare Providers enterprise team working with Kore.ai Agent Platform · Epic · Amazon Connect — pronix.ai case study
Case study · Healthcare · Conversational AI

38% call containment in 90 days for a regional healthcare provider — healthcare-safe conversational AI

A regional healthcare provider needed to contain rising call volume for scheduling, refills and pre-visit intake without adding agents. pronix.ai deployed Kore.ai Agent Platform virtual agents on voice and chat with Epic integration, PHI guardrails and HITL escalation — 38% containment in 90 days with CSAT flat.

Regional healthcare provider, 42 clinics · Kore.ai Agent Platform · Epic · Amazon Connect

Client
Regional healthcare provider, 42 clinics
Industry
Healthcare Providers
Platform
Kore.ai Agent Platform · Epic · Amazon Connect
38%
Tier-1 call containment
-24%
Average handle time on transferred calls
+0.3pt
Patient CSAT
0
healthcare audit findings

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

The challenge

Call volume was up 34% year over year, driven by appointment scheduling, medication refills and pre-visit intake. Hiring couldn't keep pace and abandon rates were climbing. Any AI rollout had to stay inside healthcare guardrails, integrate with Epic and never mis-triage a clinical symptom.

Our approach

Step 01

Bounded intents, clinical guardrails

Shortlisted three intents — scheduling, refills, pre-visit intake — and put a symptom-triage classifier in front that hard-routed anything clinical to a human within two seconds.

Step 02

Epic-native tool layer

Nine idempotent tool calls into Epic for appointment slots, medication lists and demographics. Every write journaled to Epic audit for compliance.

Step 03

Voice + chat from day one

Same Agent Platform bot flow deployed to Amazon Connect voice and the patient portal chat — one authoring surface, two channels live together.

Step 04

PHI guardrails and HITL

PII/PHI masking on every prompt, topic-scope firewall, and a warm handoff pattern that shipped the full transcript context to the agent — no repetition.

Our access center finally has room to breathe — and patients are getting appointments booked at 11pm on a Sunday.

VP Patient Access
Executive brief · 1-page PDF

Take this case study into your next steering committee.

One page: the business problem, the solution, the technical architecture and the measured outcomes — sized to drop straight into a board pack. Share your work email to unlock it; one form unlocks every gated download on this site.

For VP Patient AccessFor CIOFor Chief Digital Officer

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.

Submit a project brief

Want a similar programme in your environment?

Four fields. Tell us the outcome and timeline, and the lead for this industry replies with indicative scope, team shape and commercial options.

industryHealthcare Providers — routed to this team

Prefer to book a slot? →