We built this for Vensa Health.
Not a deck. A working AI agent that handles the questions clinic staff send to Vensa support — turning on Smart Recalls and Secure Messaging, sorting out plan tiers, adding provider seats. Try it below. The chat reads from a Vensa-shaped knowledge base and the workflows match how a Vensa specialist should actually answer.
The voice version of this agent runs on the same workflows and KB. In production it answers the Vensa support line — handles setup questions, books onboarding calls, and reads ticket numbers digit by digit when escalating.
How we built this
Honest version. Here's what's behind this chat:
Wrote Vensa-shaped knowledge
Five hero articles covering plan tiers, Smart Recalls setup, Secure Messaging, seat management, and PMS integrations. The agent quotes from these instead of guessing — pricing, prerequisites, and integration support are all exact.
Built workflows around your model
Natural-language workflows for feature setup and account/billing. The setup workflow checks the clinic's current state before proposing anything, and books a real onboarding call instead of telling them to "log a ticket".
Connected mock Vensa tools
Three mock tools — clinic profile, recent tickets, book setup call — that mirror real APIs. In production these point at your real systems with the PII handling we already do for regulated subscribers.
Went live
Published all workflows to the live environment with guardrails active — knowledge gap handling and no-weak-uncertainty steering. 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 clinic data, billing system, and the PMS integration takes a few weeks. We've done it for regulated healthcare subscribers across NZ, AU, US, and EU.
Discuss with our experts →
Demo built with