The courier sends a photo. The receipt generates itself in Rivhit.
Case study by Achiya Cohen, founder of Achiya Automation
A WhatsApp bot in the couriers' group receives a document photo, reads the details with OCR, prepares a receipt in Rivhit through the API and sends it back to the group. The flow includes a path for exceptions that need review.
Every receipt — a manual chain Photo in the group → receipt
- A courier finishes a delivery and photographs a document — and waits
- Someone at the office types the details into Rivhit by hand
- Typos = wrong receipts and credits
- In the evenings and on weekends there's no one to generate them — it all piles up
- The courier sends a photo to the WhatsApp group — and that's it
- OCR reads the details off the document automatically
- An AI agent generates a receipt in Rivhit through the API
- The receipt comes back to the group after the document is produced
Here's how it works inside
A description of each flow, with identifying details removed.
Photo in the group → OCR → receipt in Rivhit
The flow listens to the couriers' WhatsApp group and filters only relevant messages. When a photo arrives, an OCR service extracts the text from it, and an AI agent with access to the Rivhit API builds the receipt: customer, amount, line items. The receipt is sent back to the group as an attachment, and the courier drives on to the next trip.
The numbers you feel every day
Do you have a process that runs through photographing a document?
If someone at your company types documents by hand today, we can map the process and check which steps fit automation.
Want a system like this? Check out our WhatsApp bot service or our pricing & plans.