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

Read →
Case study · Healthcare · Agent assist

Agent assist across 900 seats at a healthcare provider — 22% AHT reduction with healthcare guardrails

A large healthcare provider wanted real-time agent coaching, next-best-action and auto-summary across 900 patient-access seats — without asking agents to learn a new console. pronix.ai deployed Kore.ai Contact Center AI as an overlay on Genesys Cloud with Epic-aware summaries.

Client
Integrated healthcare provider, 900 patient-access seats
Industry
Healthcare Providers
Platform
Kore.ai Contact Center AI · Genesys Cloud · Epic
By pronix.ai CX Engineering7 min readQ1 2026
-21%
AHT
+18%
First-contact resolution
-63%
After-call work
900
Seats live in 10 weeks

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

The challenge

Agents were flipping between five apps per call and after-call notes into Epic were inconsistent — CMIO flagged clinical-documentation risk. Prior agent-assist pilots had stalled because summaries were too generic to paste into an Epic encounter note.

Our approach

Step 01

Overlay, not replacement

Deployed Kore.ai Contact Center AI as a sidebar in the existing Genesys agent desktop — zero retraining on the primary console.

Step 02

Epic-shaped auto-summary

Tuned summary prompts to Epic's encounter note structure — sections, order, clinician-friendly abbreviations — so agents pasted, not rewrote.

Step 03

Real-time next-best-action on approved KB

Grounded on the sanctioned patient-access knowledge base with a topic-scope firewall that blocked any clinical advice.

Step 04

Supervisor coaching loop

Weekly review of low-confidence summaries by team leads to close the retraining loop — quality trended up every sprint.

For VP Patient AccessFor Contact Center DirectorFor CMIO

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.