We built this for Teachers Health.
This isn't a slide deck. It's a working AI agent that handles member questions about claims, finding a provider, and cover — pulling live from a mock Teachers Health data layer. Try it below. The chat reads your real help-centre style content and the workflows match how a Teachers Health agent should actually behave.
The voice version of this agent runs on the same workflows and KB. In production it answers the Teachers Health main line 24/7 — handles claim status checks, reads membership numbers and dollar amounts digit-by-digit, and looks up nearby Member Plus providers for a member.
How we built this
Honest version — no smoke. Here's exactly what's behind this chat:
Scraped your help centre
Crawled teachershealth.com.au public FAQs into the agent's knowledge base. The agent quotes from this when members ask about waiting periods, cover, joining, and member rewards.
Built workflows around your model
Wrote natural-language workflows for claim status, finding a provider, and routing. Each one quotes membership and claim details back to the member before any action and never narrates "let me check".
Connected mock Teachers Health tools
Wired in three mock tools — member profile, recent claims, find a provider — that mirror real APIs. In production these point at your real systems with PII handling we already do for our regulated subscribers.
Went live
Published all workflows to the live environment with guardrails active — knowledge gap handling, no-weak-uncertainty steering, and de-escalation for upset members. This page talks to that live agent.
Want to build the real one?
This took us ~90 minutes with one engineer. Production with your real KB, real member records, and provider integration takes a few weeks. We've done it for regulated healthcare subscribers across AU, US, and EU.
Discuss with our experts →
Demo built with