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
Self-storage managers miss calls while they're out on the lot, and callers who reach voicemail usually rent somewhere else.
So I built StoreRight, a demo AI receptionist on Vapi + Twilio. It answers in about a second, 24/7, quotes from live unit inventory, reserves the unit, books the tour and texts the confirmation. It also takes tenant payments and resets gate codes after checking who's calling.
Every call shows up in an operator dashboard (leads, tenants, payments, inventory).
You can call it yourself and try to reserve a unit: https://voicedesk-h31g.onrender.com/agent/receptionist
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
Hi! Sharing my new project: a CRM dashboard for dental clinics 🦷
A day timeline for every chair, patient records with tooth charts, and a voice AI assistant for the front desk.
I’d really appreciate your support and feedback ❤️
Full project
The blue-grey in the dashboard reminds me of Porsche's color. Looks elegant and powerful at the same time. Love this kind of minimal grey.
Worth a read if you're building AI support for e-commerce.
UI Trax gets the hard parts right: answers grounded in real store data, order lookups only after verification, a guard on every reply, and a clean handoff to humans with an AI summary.
Reliable AI agents come from architecture, not just prompts. This case study shows it.
#AIAgents #Ecommerce #CustomerSupport #AI
Check it out
The verification step before an order lookup caught my attention. For patient intake, I would similarly verify identity before retrieving records and limit the handoff summary to what staff need. I would also flag uncertainty rather than presenting an unverified summary as fact.
Just published a new case study: UI Trax, an AI customer agent for online stores. 🚀
Most store chatbots either follow rigid scripts or make things up. I built one that does neither.
What it does:
• Answers from real store data (products, sizes, stock, prices) through tool calls, never from guesses
• Tracks orders only after verifying the customer's phone number
• Runs a guard on every reply that blocks invented links, discounts, policies and promises
• Hands off to a human with a one-line AI summary, then goes quiet when staff join
• Works on web chat and WhatsApp, in English and Roman Urdu
Built with Python and Gemini, and tested against 1,500+ conversation scenarios.
Full breakdown with screenshots is in my portfolio. Open to projects building AI support agents for e-commerce, clinics, real estate and service businesses.
Great work on the case study!
