Unveil Logo
← Back to all work
Capability build Health insurance · Member acquisition

AI dental-insurance broker chatbot — a capability build

Long-form conversational AI for dental-insurance shoppers — frontier LLM with function-calling to filter, retrieve, and explain ACA marketplace dental plans.

Category
Capability build
Industry
Health insurance · Member acquisition
Role
Architect, lead engineer (proof-of-concept)
Scope
Conversational AI assistant over a structured ACA dental-plan dataset, with plan-brochure retrieval and a guided conversation flow
Duration
Open-source proof-of-concept
Capabilities
Generative AI Conversational Interfaces LLM Function-Calling Structured Data Retrieval Plan Comparison & Recommendation

What this is

An open-source generative-AI proof-of-concept we built to demonstrate that a long-form conversational AI assistant can replace — or sit alongside — the rigid “plan compare” forms most insurance marketplaces still use. The assistant (“Pearl”) helps a dental-insurance shopper pick a plan by chatting through their location, plan-type preference, price sensitivity, and family situation, then filters a real ACA marketplace dental-plan dataset and recommends suitable plans with full coverage detail and a link back to the source brochure.

It is a proof-of-concept, not a production system — but the underlying patterns (function-calling over a structured dataset, persona-driven conversation flow, deflect-to-human safety net) are the same ones we apply in production client work.

A live walkthrough and source review are available under NDA.

What it does

Built with

LayerStack
ModelLeading frontier LLM, with function-calling
Frontend / UIStreamlit
DataACA marketplace dental-plan dataset + per-plan brochure markdown
Data handlingPython data utilities
Backend languagePython
SecretsEnvironment variables / Streamlit secrets

What this means for you

If you operate a marketplace, broker, member-facing acquisition flow, or any product where users need to navigate a structured catalog of options through conversation rather than through a sequence of dropdown filters, we can:

Want to talk about a similar conversational-marketplace problem? Contact us.

Ready to talk about your project?

We respond within one business day.

← See all work