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

Read →
Case study · Healthcare · Omnichannel CAI

Omnichannel conversational AI at a large healthcare provider — one bot across voice, web, SMS and app

A large healthcare provider was maintaining four separate bot stacks across voice, web, SMS and the MyChart app — with drifting answers and duplicated compliance reviews. pronix.ai consolidated to a single omnichannel conversational AI on Kore.ai with 44% containment and one review cycle.

Client
Large integrated healthcare provider, 6M patients
Industry
Healthcare Providers
Platform
Kore.ai Agent Platform · Amazon Connect · Twilio · MyChart
By pronix.ai Strategy Practice9 min readQ1 2026
44%
Cross-channel containment
-70%
Compliance review cycles
1
Bot stack instead of four
+0.4pt
Patient digital CSAT

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

The challenge

Four bot stacks meant four teams, four compliance reviews and four sets of answers that could diverge on the same policy question. Patients got different answers on chat vs voice — CDO wanted one truth, four channels.

Our approach

Step 01

Single authoring surface

One Kore.ai Agent Platform project, one intent taxonomy, one knowledge grounding — deployed via channel adapters to voice, web, SMS and MyChart.

Step 02

Channel-native UX, shared brain

Voice used SSML and barge-in; SMS collapsed to short structured turns; MyChart used rich cards. Same reasoning under the hood.

Step 03

One compliance review

Combined the four separate review cycles into one — legal and compliance signed off on the intent, not the channel.

Step 04

Escalation continuity

Cross-channel context handoff — patient starts on SMS, escalates to voice, agent sees the full transcript with no repetition.

For Chief Digital OfficerFor CIOFor VP Patient Experience

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.