We built this for InstantScripts.
This isn't a slide deck. It's a working AI agent that handles patient questions about prescription status and repeat requests — pulling live from a mock InstantScripts data layer. Try it below. The chat reads your real help-centre style content and the workflows match how an InstantScripts agent should actually behave.
The voice version of this agent runs on the same workflows and KB. In production it answers the InstantScripts main line 24/7 — handles repeat requests by phone, reads prescription IDs digit-by-digit, hands off to a doctor for clinical calls.
How we built this
Honest version — no smoke. Here's exactly what's behind this chat:
Scraped your help centre
Crawled instantscripts.com.au public help content into the agent's knowledge base. The agent quotes from this when patients ask "how does it work" or "what does it cost".
Built workflows around your model
Wrote natural-language workflows for prescription status, repeat requests, and small talk. Each one quotes prescription details back to the patient before any destructive action and never narrates "let me check".
Connected mock InstantScripts tools
Wired in three mock tools — patient account, recent prescriptions, request repeat — that mirror the 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 — medical safety triage, weak-uncertainty steering, and escalation patterns tuned for healthcare. 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 clinical sign-off takes a few weeks. We've done it for regulated healthcare subscribers across AU, US, and EU.
Discuss with our experts →
Demo built with