The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
Pestle: an AI phone line for UK pharmacies that knows its limits
Pestle answers a pharmacy's phone line on Retell AI and Twilio. It handles routine questions (hours, services, prices, collection and delivery) only from information the pharmacy has approved, and it books appointments.
What it never does: state prescription status, stock or clinical information. Those go straight to staff. A caller asking for a person is transferred immediately, with a callback offered if nobody answers.
A caller's number is treated as a hint, never as proof of identity. Patients are verified in code. Each pharmacy is a separate tenant, and the design follows UK GDPR, because health data is special category data.
Try the demo (fictional data): pharmacy.adaptivesystems.dev/#try
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Related posts
Healthcare AI Agent – Reschedule Appointments by Voice
AI Healthcare Assistant — Turn On Sound for the Best Experience.
Movexa AI Assistant helps physiotherapy clinics reschedule patient appointments in seconds, by text or by voice, without leaving the dashboard.
THE PROBLEM
Rescheduling a single session in a busy clinic means checking the therapist's calendar, finding a free slot, updating the booking and remembering to notify the patient. Front desk staff and therapists repeat this many times a day across different tools, and missed reminders lead to no-shows.
THE SOLUTION – THE FLOW
Ask – Open the AI search (⌘K) or tap the mic and say: "Reschedule Tezah's session tomorrow to 4 PM and remind her."
Understand – Voice mode transcribes live and shows exactly what the AI understood.
Check – Movexa checks the therapist's calendar and finds that 4:00 PM is free.
Confirm – The AI never acts silently. It shows a clear action card (patient, old time, new time, therapist, reminder) to confirm, edit or cancel.
Done – The appointment moves, the patient gets an SMS + app reminder, and the change is logged with one-tap Undo.
THE RESULT
A task that took several clicks and calls now takes one sentence, while the clinic team stays in full control of every action.
Most AI apps work like this: the model decides, the app saves, and the user finds out later that the numbers are wrong. 😬
For Notarik, I set one rule. The AI can only propose. Nothing gets saved until the user confirms. ✅
🧾 What it does
Take a photo of a receipt, or type "lunch 45k at the warung". You get a categorized expense, a monthly recap, and a chat assistant you can ask things like "where did my money go this month?":
🔒 The parts I care about most
• Receipt totals are checked by plain code, not by the model. If the math doesn't add up, it gets flagged.
• Money is stored as whole numbers (IDR), never decimals, so there are no rounding bugs.
• Every user's data is locked at the database level with Postgres row-level security. Even if the app has a bug, it can't show someone else's records.
• Text on a receipt is treated as untrusted. If a receipt says "ignore your instructions", it's just text.
• The agents have tests, so when I change a prompt I can see right away if it got worse.
🛠 Built with Next.js, React Native, Python (FastAPI), LangGraph and PostgreSQL. One person, web and mobile, from design to API.
🤝 If you're building something where an AI touches real money, records or user data, this is the kind of work I like: agents that are useful and also safe to put in front of users.
👉 Try it live: https://notarik-app.nashir.tech
Want to talk about yours? Send me a message.
Smart call keeping the confirmation.
I gave a dental clinic a receptionist that never sleeps. 🦷
Today I finished building a WhatsApp AI Receptionist — and tested it live, end to end.
A patient messages the clinic on WhatsApp. Within seconds they get a polite, human-sounding reply with the clinic's REAL fees, timings and doctors — because the AI answers only from the clinic's own database. It never invents a price. If it doesn't know, it says it will confirm with the owner.
The honest part? Halfway through testing, it broke. Spectacularly. 😅
WhatsApp sends invisible "delivered" signals — and my system was answering those signals too. 192 executions later, I found the cause hiding in one execution log: no message, just a delivery status. One guard node later, the loop was dead and the replies were clean.
That debugging session taught me more than any tutorial:
→ Always guard your trigger. Not every webhook event is a message.
→ Read the raw execution JSON before guessing. The answer is always in there.
Now I'm setting this up for clinics and local businesses that live on WhatsApp — instant replies, appointments captured, every lead saved, even at 2 AM.
If your business answers the same 10 questions on WhatsApp every day — what would you automate first?
