We built this for City Fertility.
Not a slide deck. A working AI patient agent that handles appointment and funding questions using a mock City Fertility data layer. Chat below, or call the voice line. The agent stays strictly out of clinical advice — anything diagnostic routes to a nurse.
Try asking about your treatment plan, an appointment, or the cost of a cycle. Anything clinical hands off to a nurse.
How we built this
Honest version. Here's what's behind this chat:
Wrote City Fertility-shaped knowledge
Five hero articles covering cycles, costs, Medicare safety net, appointment management, and stimulation. The agent quotes from these instead of guessing — and breaks the fourth wall when it doesn't know.
Built workflows for two real flows
Natural-language workflows for appointment management and funding questions. Each routes to a nurse the moment anything clinical comes up. The funding workflow offers a personalised quote escalation.
Connected mock City Fertility tools
Three mock tools — patient profile, upcoming appointments, and reschedule confirmation — that mirror a real PMS. In production these point at your real clinic systems with the PII handling we already do for regulated healthcare subscribers.
Went live with guardrails on
Published to the live environment with the no-weak-uncertainty guardrail steering every response. Tested across 10 scenarios — see the report.
Want to build the real one?
This took us a focused afternoon with one engineer. Production with your real KB, real patient records, and the clinic PMS takes a few weeks. We've done this for regulated healthcare subscribers across AU, NZ, US, and EU.
Discuss with our experts →
Demo built with