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

Read →
Case study · Retail · Conversational AI

41% self-service containment for a national retailer — order status and returns on conversational AI

A national retailer wanted to contain repetitive order-status and returns calls without hurting the high-touch loyalty experience. pronix.ai deployed Kore.ai Agent Platform on voice and chat over Genesys Cloud with Salesforce Commerce integration — 41% containment and CSAT up half a point.

Client
National retailer, 3,100 agents
Industry
Retail & Ecommerce
Platform
Kore.ai Agent Platform · Salesforce Commerce Cloud · Genesys Cloud
By pronix.ai CX Engineering8 min readQ1 2026
41%
Containment on top-3 intents
+0.5pt
CSAT
-19%
AHT on escalated calls
12 wk
First intent live to peak-ready

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

The challenge

70% of contacts were three intents — order status, returns and loyalty balance — but the previous chatbot only handled 12% end-to-end. Leadership wanted containment without a wave of angry loyalty-member escalations at peak.

Our approach

Step 01

Intent-first, tier-based rollout

Shipped the top three intents first, then expanded. Loyalty tier ≥ Gold was routed to a human by policy — containment metric was measured net of that carve-out.

Step 02

Search AI grounding on the product catalog

Grounded returns policy, item eligibility and store hours on the live catalog instead of a static KB. No stale answers when policy changed.

Step 03

Voice + chat single-source authoring

One Agent Platform flow deployed to Genesys voice and the storefront chat — content team maintained one script, not two.

Step 04

Peak-week guardrails

Hard cap on new intents in the six weeks before Black Friday; only guardrail tuning was allowed. Zero peak-week regressions.

For VP Contact CenterFor Head of DigitalFor CX Platform Owner

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.