Bank slips, read by AI.

Paper slips, ATM receipts, online-transfer confirmations, banking-app screenshots. Whatever your customers upload, our fine-tuned models turn it into structured, verified metadata with a confidence score on every field. One API call.

Talk to us See how it works
Input · customer upload
SAMPLE BANK PLCCASH DEPOSIT
BranchColombo 07
Date02 / 08 / 2026 · 14:31
Account No.01 · 5 · 002 · 4 · 08812
AmountRs. 12,500.00
ReferenceDEP-88214763
Deposited byW. A. Perera
TELLER 04 · 1431
POST /v1/slips/extract200 OK
{
"bank": "Sample Bank PLC",99%
"branch": "Colombo 07",98%
"date": "2026-08-02",99%
"time": "14:31",96%
"amount": "LKR 12,500.00",98%
"reference": "DEP-88214763",97%
"depositor": "W. A. Perera",74%
}
✓ 6 fields auto-cleared·✓ no duplicate found·1 field → review queue
Why platforms plug it in

We run the AI. You get clean metadata.

Slip verification is a full-time machine-learning problem: formats change, photos are bad, and mistakes cost money. We own that problem end to end and hand your platform a simple API.

Every slip format
Paper deposit slips, including partly handwritten ones, plus ATM and CDM receipts, online-banking confirmations, and mobile-app screenshots, across all major Sri Lankan banks and payment apps.
20+ fields per document
Transfer amounts separated from bank fees, dates and times, both banks, account numbers, depositor details, remarks, and every reference number printed on the slip.
Confidence on every field
Each extracted field carries its own 0–100 confidence score, so you decide what auto-approves and what gets a human look.
Fraud signals built in
Duplicate detection across references and re-uploaded images, tampering suspicion, and photo-of-a-screen flags, all returned before you release the payment.
API-first and fail-safe
One REST call in, structured JSON out. If extraction fails, you get a clean, typed error to fall back on, so payments don’t get stuck waiting on the AI.
We own the AI lifecycle
Fine-tuning, evaluation, and retraining when banks change their formats. Already running in production on The Search Bar, our EdTech platform serving 80,000+ users.
How it works

From photo to verified payment.

01
Send us the slip
Your platform POSTs the customer’s upload (photo, screenshot, or PDF) to the extraction endpoint.
02
Our models read it
Fine-tuned models extract 20+ fields: banks, branches, dates, amounts split from fees, reference numbers, and depositor details, plus tampering and duplicate signals.
03
You get structured JSON
Every field comes back paired with its own confidence percentage, ready to match against your expected payment.
04
You stay in control
The AI never approves or rejects on its own. Auto-approve above your confidence threshold and hold the rest for review.
Who it's for

Anywhere customers pay by bank slip.

If your operations team spends hours a day squinting at deposit slips, this API pays for itself quickly.

EdTech & course platforms
Verify class fees and subscriptions the moment students upload their slips, with no overnight backlog before access unlocks.
E-commerce & bank-transfer checkout
Confirm direct-deposit orders automatically and release fulfilment without manual reconciliation.
Subscriptions & memberships
Match recurring deposits to member accounts using references and amounts, month after month.
Utilities, finance & collections
Process high volumes of branch and ATM deposit slips with an audit trail of every extraction.
More from BetaGen
AI Slip Checker

Ready to stop checking slips by hand?

Tell us about your platform and your deposit volumes. We’ll run a pilot on your real slips and show you the accuracy numbers before you commit.

hello@betagen.org