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
AI Receptionist & Booking Agent for Austin's Sharpest Fades — Austin's #1 rated barbershop.
Built in Lovable to automate bookings and customer service:
Answers FAQs (services, prices, hours, location)
Recommends cuts based on face shape/hair type
Quick-reply flows: "What's the price?", "What cut suits me?", "Book 3pm"
Collects name, phone, date/time & guides to booking + payment
Ready for integrations: Calendar, Stripe Payments, CRM, WhatsApp/SMS
Stack: Lovable, Luna, HTML/CSS/JS, API workflows
Goal: Reduce no-shows, increase bookings, 24/7 AI receptionist.
Live demo available.
The demo flow in the screenshots reads really naturally, and recommending cuts by face shape is a clever touch that makes it feel personal rather than robotic. Have you seen it reduce no-shows in practice yet?
Thanks Timothy! Appreciate the feedback.Yes in early testing in 2 barber shops, the AI follow up & text confirmation cut no shows from 30% to under 10%. Still collecting more data but the personal touch seems to help clients actually show up
When the agent offers a time, is that slot locked right away? If two customers get the same slot in one minute, which one gets it?
Yes, when the first person picks that slot, it locked and you have to choose another
Clean flow. The "Book 3pm" quick reply is exactly how people text a barber.
Yeah exactly
Recommending cuts by face shape is a nice touch. I recently built a voice-first booking site for a tour business on Lovable, so I know how many edge cases hide in booking. How does yours handle reschedules?
For reschedules, it been handled in three ways: 1- in conversation: user can say “user can say re-schedule for Friday” and the voice agent checks calendar availability live via ApI and moves the event
2- post booking links: every confirmation text has a magic link to...
The confirmation text plus follow-up going from 30% to under 10% no-shows is a strong result for a booking agent. Since it's wired for Calendar and Stripe, I'm curious how you handle a payment that fails or a slot that gets taken mid-conversation.
That 30% to 10% for results! for payments: stripe is in auth and capture mode. if payment fails we don't block the slot we hold it for five minutes and retry then send a payment link via SMS. If it fails again, slot auto release back to calendar
For mid-conversation race...
Nice build Ibrahim. Booking is where most of the real value is for local businesses. I built a voice receptionist for HVAC companies, and the after hours calls turned out to be the biggest win.
Thanks Muhammad, after hours is the real money. Love the voice receptionist idea for HVAC, great win. I actually built that too.
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
AI Customer Support Agent for Web Form, Gmail & WhatsApp
An AI support agent that answers customer questions across a web form, Gmail and WhatsApp, and hands off to a human team when it should. Load-tested with 200+ messages and no lost messages.
I built an AI customer support agent as a demo for a fictional SaaS company called Flowmint. Customers can write through a web form, Gmail or WhatsApp. The agent finds the answer in a knowledge base, replies on the same channel, and passes the conversation to a human team (Billing, Sales, Support) for refunds, special pricing, or when a customer asks for a person.
One agent for three channels, with replies formatted for each (a clean HTML email, a short WhatsApp message, a private web tracking page)
Safety rules written in code: it can only quote approved prices, and refunds always go to a human
Remembers returning customers on email and WhatsApp
Private ticket tracking page with a secret tracking code
If the AI service is busy, it switches to backup AI models, and to a knowledge-base answer if all are limited
I load-tested the agent for 24 hours with 200+ messages across all three channels, using simulated customers plus real emails and WhatsApp messages I sent myself.
212 messages in, 212 replies out, none lost
Only 3.3% needed a human
Areas I’m improving: faster replies with a paid AI plan, and spam protection for the web form.
Tech stack: Python, FastAPI, OpenAI Agents SDK, Kafka, PostgreSQL, Next.js, Docker, Gmail API, WhatsApp Cloud API.
Writing the safety rules in code, not in the prompt, is the part I like most: approved prices only, and refunds always go to a human. My RAG demo also passes the question to a person when the guide has no answer. How does your agent decide that a customer "asks for a person": a fixed list of phrases, or does the model decide?
Agentic AI Development in Australia
What if your AI could not just answer questions but actually get work done?
That is the idea behind Agentic AI Development in Australia. We build AI agents that plan, make decisions and carry out multi step tasks on their own, from research and data processing to handling routine business workflows.
Instead of another tool your team has to manage, you get a digital teammate that works in the background.
If you want to see what agentic AI could automate in your business, take a look at our services here: https://aiventechnologies.com/agentic-ai-development-in-perth-australia/
A modern, elegant website concept designed for J. Michaels Salon, showcasing a premium beauty and wellness experience.
The design combines sophisticated typography, warm neutral tones, golden accents, and beautiful interior imagery to create a luxurious and welcoming digital experience.
The homepage features a clean navigation system, an immersive hero section, elegant visual presentation, and a clear call-to-action that guides visitors towards exploring the salon's products and services.
