Healthcare · 29 Locations
AI booking support across 29 locations. 78% less abandonment.
Deploying AI agents with tool calling across Canada's leading ultrasound brand — from knowledge base to live customer support.
How UC Baby partnered with SundayPyjamas to build an AI support agent that handles package recommendations, location lookups, and gestational timing guidance — serving 85% of customer inquiries without staff intervention.
UC Baby
Today
Package for 28 weeks?
Nearest clinic in BC
UC Baby Support
Recommend 3D package for 28 weeks
0%
Inquiries handled by AI
0%
Recommendation accuracy
0%
Less booking abandonment
0
Locations nationwide
The problem
UC Baby operates 29 ultrasound clinics across Canada. Expectant families had complex questions about gestational timing, package details, and location availability. Without immediate answers, customers abandoned booking or called multiple locations.
Front desk teams were overwhelmed with repetitive inquiries, reducing capacity for in-clinic service. Booking abandonment was the core bottleneck.
What we built
We deployed an AI support agent with tool calling for package recommendations, location lookups, and contextual booking guidance — grounded in UC Baby's service catalog and gestational timing guidelines.
The agent handles 85% of inquiries without staff intervention while preserving safety boundaries for healthcare consumer interactions.
What we built for UC Baby
- AI agent with tool calling for package recommendations and location lookups
- Knowledge base over service catalog, pricing, and gestational timing guidelines
- Multi-location support across 29 clinics with location-specific availability
- Analytics dashboard tracking agent performance, conversion, and satisfaction
Technical integration
Tool calling for package matching, location availability, and knowledge retrieval over the full service catalog.
Package recommendation
Tool calling → service cataloggestationalAge → matched packages
Location lookup
Tool calling → availabilitypostalCode → nearest locations
Knowledge retrieval
File search over knowledge basequery → grounded response
Booking guidance
Contextual agent responseintent → package + CTA
Geographic coverage
Serves customers across all Canadian provinces with location-specific availability and postal-code matching.
See it in action
Outcomes
85% of inquiries handled by AI across all 29 locations. Package recommendation accuracy at 92%, booking abandonment down 78%. Front desk teams focus on in-clinic experiences.
The system understands gestational age windows for gender testing, 3D/4D imaging, and late-term fetal position scans — accurate recommendations instead of generic responses.
“The AI agent handles the majority of our customer inquiries — from package recommendations to booking guidance. Our staff can focus on the in-clinic experience.”
What this enables for healthcare networks
The UC Baby pattern applies to other multi-location healthcare deployments:
Multi-location clinics
Service matching and availability across any number of locations from one knowledge base.
Patient intake & triage
Context-aware routing based on symptoms, history, and provider availability.
Insurance & billing
Knowledge retrieval over coverage policies for accurate pre-booking estimates.
Building something similar?
Working proof-of-concept on your data in 10 days.