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
WhatsApp Payment Verification AI Agent — n8n + OCR + Stripe + FastAPI (Production, Live Client)
Built and deployed a production-grade WhatsApp AI Agent that automatically
verifies payment screenshots against live Stripe data — no manual review,
no false approvals, running 24/7.
This was delivered for a real client and is currently live on DigitalOcean.
HOW IT WORKS:
Customer sends a payment screenshot via WhatsApp
Agent downloads and runs OCR (Tesseract) to extract: Amount, Ref ID, Date, Status
Extracted data is verified against live Stripe API — not the screenshot alone
Agent returns one of three decisions instantly via WhatsApp: ✅ Approved — Stripe confirmed exact match ⚠️ Requires Review — no exact match found ❌ Not Approved — verification rules not satisfied
FRAUD RESISTANCE BUILT IN:
Duplicate detection via perceptual image hashing (DUPLICATE_IMAGE_PHASH_RECEIPT_EVIDENCE) — the same screenshot cannot be reused for a second approval
Safe-fail design: visually convincing receipts are NOT auto-approved unless Stripe confirms them
Idempotency at the message level prevents replay attacks
PRODUCTION STACK:
WhatsApp: Node.js + Baileys
Backend & OCR: Python + FastAPI + Tesseract
Workflow Automation: n8n
Payment Verification: Stripe API (Live mode)
Deployment: Docker + DigitalOcean (24/7)
DELIVERABLES:
✔ Fully automated, end-to-end payment verification pipeline
✔ Three-state decision engine (Approved / Review / Not Approved)
✔ Duplicate screenshot detection
✔ Deployed and running in production — not a demo
Portfolio: https://ibadat-ali-portfolio.vercel.app
"My work is done when you no longer need me." — Ibadat Ali
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
So I Recently rebranded my upcoming AI Agent Harness from "Crank" to "Pixie" which is the name of my cat. Do you think it was the right decision?
Which one do you prefer? Crank or Pixie?!
Check it out here: pixie.ecnivs.com
#FreelancerLife #AIHarness #FrontendDesign #AIAgent #ArtificialIntelligence #WebDevelopment #Design #TasteTest
5 voted
71%
2 voted
29%
7 votes
Closed
Pixie gets my vote too. Naming it after your cat makes it memorable, and it feels a lot friendlier for a tool people trust with their code. Nice rebrand.
GlowHaus Studio — From Inquiry to Confirmed Booking
GlowHaus Studio is a solo beauty salon based in Takoradi, Ghana, where most customer appointments are currently handled manually through WhatsApp.
The problem is simple: customers ask about services and availability, while the owner has to check her schedule, respond to messages, confirm appointments, send reminders, and handle rescheduling — creating unnecessary back-and-forth and increasing the risk of missed appointments.
I designed and built a streamlined booking experience that turns the entire process into a simple self-service flow:
Choose a service → Select an available date → Pick a time → Enter details → Confirm → Booked.
The experience also supports appointment confirmation, cancellation, and rescheduling, giving customers more control while reducing repetitive administrative work for the owner.
The goal was not simply to create a beautiful booking interface, but to solve a real operational problem: helping a small business spend less time managing appointments and more time serving customers.
Built with Lovable.
Lovely 😍
"Businesses lose time and money to invoice errors that go unnoticed until it's too late. I built an automated pipeline that extracts invoice data, cross-checks it against vendor history, and flags anomalies with clear AI-generated reasoning — all visualized in a real-time dashboard. Stack: LangChain, Groq, n8n, FastAPI, Next.js."
