DOCUPIPE
Solutions
Resources
Pricing
Huliot Group automates Hebrew purchase order processing with DocuPipe
Huliot Group is proud to be a global leader in advanced flow systems, designing, manufacturing & marketing complete solutions for water supply, wastewater & infrastructure. With automated document processing powered by DocuPipe, Huliot Group extracts and classifies Hebrew purchase orders across its companies, automatically feeding structured data into their Priority ERP and accelerating order fulfillment.
Challenge
For manufacturers serving a diverse customer base, purchase order processing is a constant bottleneck. Every order that arrives by email must be converted into a sales order before production can be scheduled. The faster that conversion happens, the faster product ships.
But purchase orders don't arrive in a standard format. Every customer sends them differently — different layouts, different field names, different PDF formats.
Huliot Group, a global leader in advanced flow systems, faced this across its companies processing a large volume of purchase orders arriving by email. Every batch of orders looked different.
"Our customers send us purchase orders in all kinds of formats. We needed a way to handle that variety automatically," says Aviran Ben Moshe, AI Lead at Huliot Group.
On top of the format variety, every document was in Hebrew — a right-to-left language that most document processing systems handle poorly. Huliot needed a solution that could handle both challenges and feed structured data directly into their Priority ERP system.
Solution
Huliot evaluated multiple solutions but most broke on Hebrew. DocuPipe was one of the only platforms that handled it natively — and during proof-of-concept, it extracted data accurately across the full range of PDF formats Huliot's customers send.
DocuPipe's team worked directly with Huliot to build and tune the initial extraction schemas — handling complex business logic like dual SKU extraction (customer SKU and supplier SKU), branch identification from PO number prefixes, and customer-specific rules for how fields should be interpreted. The onboarding was hands-on: document samples were reviewed together, edge cases were identified, and schemas were iterated until extraction met production standards.
From there, the implementation started with the highest-volume company and expanded across the organization. Purchase orders arriving by email now feed directly into the automated pipeline, with structured data inserted automatically into Huliot's Priority ERP.
Results
Native Hebrew extraction
What seemed like the hardest requirement turned out to be straightforward. DocuPipe's extraction works with common patterns in Israeli business documents — Hebrew addresses, phone numbers, and date formats — without any special configuration.
From onboarding to ownership
DocuPipe's team built the initial schemas for Huliot's most complex document types — but the goal was always to hand over the keys. Once the foundation was in place, Huliot's team took over day-to-day management: refining schemas, adding new document types, and expanding across their companies on their own.
"The changes you made are amazing! I'm already up and running with the schemas," says Ben Moshe.
Today, Huliot manages their extraction pipeline independently — iterating schemas and configuring workflows without needing to file support tickets or wait on DocuPipe for changes.
Direct Priority ERP integration
Once an order completes extraction, a webhook triggers a Make.com integration that maps the extracted data directly into Huliot's Priority ERP. Purchase order data flows from email to ERP without manual intervention.
Huliot's team configured the data mapping themselves using DocuPipe's webhook output and Make.com's workflow builder. No custom development required. No integration consultants.
The DocuPipe team got us set up fast, and now thousands of purchase orders get processed every month without anyone touching them.
Read more
Customer Stories
Bardavon Health Innovations
Healthcare
Customer Stories
PFM
Finance
Insights
The Enterprise Document AI Infrastructure: Built for Zero-Trust & Legacy Scale
Ready to get started?
Create an account and start extracting data from documents - no contracts required. Or, contact us for enterprise pricing.