We built this for Tend Health.
Not a slide deck. A working AI agent that handles patient questions about appointments and repeat prescriptions, pulling live from a mock Tend data layer. Try it below. The chat reads Tend-style help content and the workflows match how a Tend agent should actually behave.
The voice version of this agent runs on the same workflows and KB. In production it answers Tend's main line 24/7 — handles appointment queries, books repeat scripts by phone, reads NHI numbers digit by digit, and points patients to a clinician when something is clinical.
How we built this
Honest version. Here's what's behind this chat:
Wrote Tend-shaped knowledge
Five hero articles covering booking, rescheduling, repeats, fees, and enrolment. The agent quotes from these instead of guessing — fees are exact, eligibility rules match the website.
Built workflows around your model
Natural-language workflows for appointments and prescription repeats. Each confirms identity, identifies the patient's care team, and never invents medication names or doses.
Connected mock Tend tools
Three mock tools — patient profile, recent appointments, request a repeat — 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 — no hedging, knowledge gap handling, 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 KB, real patient records, and the Tend app integration takes a few weeks. We've done it for regulated healthcare subscribers across AU, NZ, US, and EU.
Discuss with our experts →
Demo built with