--- title: "Document AI workflow automation | YPAI" url: https://ypai.ai/document-ai-workflow-automation/ description: "Document workflows that read what arrives, check it against your order, case or register, send each exception to a named owner and write the record once." source: "src/copy/routes (route /document-ai-workflow-automation/)" --- # The paper said ten. Nine arrived. > Document workflows that read what arrives, check it against your order, case or register, send each exception to a named owner and write the record once. Document-triggered work, completed in the systems you already run. On this page one delivery note is classified, read, checked against the order, stopped, handed to the person who counted and written once. - **Your browser**: the checks, the owner and the record run here - **The OCR model**: an open-source model read the example page - **Requests to other servers**: counted from the moment you run the check An example note. Nordvik Emballasje AS and Fjellheim Varehus AS are invented companies. A recorded read by an open-source OCR model, on the flat page, on one CPU, on 18 September 2026. The boxes are drawn on the photograph where the model found each line. The check, the owner and the record below run live in your browser. Runs in your browser. No customer data. ## Three pages came stapled together. The reader finds the nine. A delivery note of two pages, and a letter that does not belong to it. The letter is held for a person. Page two is read in 56 lines: the printed ten, the strike through it and the handwritten nine beside it are three of them. - unknown · held for a person - delivery note · 1 of 2 - delivery note · 2 of 2 - **class**: delivery note · 2 of 2 - **supplier**: Nordvik Emballasje AS - **note**: PS-2026-08871 - **item**: IBC-1000 - **ordered**: 10 - **received**: 9 ## The value was read correctly. The delivery still stops. Ten in the order, ten in the electronic invoice, nine in handwriting on the note. The comparison runs in your browser on the value the model read. Move the count and the verdict moves with it. Received must equal ordered before the receipt is written. A checksum that fails stops the note before the count is compared. Counted in your browser from the moment you run the check. the bundled example, until you run the check ## The exception goes to the person who counted. One answer releases it. The stop reaches the goods receipt owner with the evidence attached: the handwriting, cropped from the page, and the rule the count broke. Their answer runs the check again and releases the record. received 9 differs from ordered 10 The owner accepted 9 received. One outstanding. The record is released. Corrected by the owner to {n}. ## Nine received, one outstanding. Written once, even when the system was down. The receipt is written into the system of record you name, with the page and the line each value came from. Switch the system of record off: the write waits, retries and is written once when the system is back. - **fields read**: 6 - **rules passed**: 1 of 2 - **decided by a person**: 1 - **written**: 1 of 1 - **order**: ORD-45120 - **item**: IBC-1000 · IBC-container 1000 l - **received**: 9 of 10 - **decided by**: goods receipt owner · 17 September 2026, 14:40 The receipt lands where the rest of your records are. A sample record from the example note. Move the count above and the record follows. ## Four kinds of work still arrive on paper. One workflow. In Norway the business invoice becomes structured data by law. The note, the claim, the form and the contract still arrive as pages. Each is read, checked against what it must agree with, and handed to an owner when the two disagree. Swipe sideways to see the other kinds. - delivery notes, packing lists and foreign supplier invoices - the order and the electronic invoice - the policy and the case file - identity documents, forms and signed consents Your document kinds are named at scoping. The workflow is the same one shown here. ## What counts as accepted is written down first. The pilot is judged against it. Three things are agreed before the first production document is read. - **The classes and the schema**: Which documents arrive, what each one must yield, and what an unknown is held as. - **The evaluation set**: Your documents, including the ones that must stop. - **The rules, the thresholds and the owners**: Which rule stops a document and who owns each exception, with thresholds agreed in the statement of work. Four places, the same four the deployment page names: your cloud, a dedicated EEA tenant, a hybrid split or your own hardware. The documents stay inside the boundary you agree before release. - [Private and enterprise deployment](https://ypai.ai/ai-implementation/private-enterprise-deployment/) ## Bring the documents and the decision they should trigger. Three lines are enough. ### What arrives - The kinds of document, and how they come in. ### What it must agree with - The order, the case, the register: the system of record. ### Who owns the exception - The person a stopped document goes to. A named project lead reads it and replies inside one EU business day with a first read on the classes, the rules and the evaluation set. What arrives, what it must agree with, who owns the exception Read from your brief. Edit it if it is wrong. A named project lead reads what arrives and replies inside one EU business day with a first read on the classes, the rules and the evaluation set. The rules you sign start as these three lines. ## What operations, finance and IT ask first. ### What does the workflow cover? Classification, extraction, validation, review, routing and the system update, built as one workflow. On this page they are the read, the stop, the owner and the record. ### Which documents can it read? Printed pages, handwritten entries on them, scans and photographs of pages, and files that already carry text. Each class is named before the build, with what it must yield and what an unknown is held as. ### What happens to a document the system does not recognise? It is held as unknown for a person, together with the pages it came with. Extraction starts when that person names it. ### Where does the extracted value go? Into the system of record you name, once, after the rules have passed or a person has decided. The record carries the page and the line each value came from. ### Who decides an exception? The owner named for that rule. The exception reaches them with the crop from the page and the rule it broke, and their answer releases or corrects the record. ### Does the invoice still need reading? In Norway the invoice between bookkeeping-liable businesses becomes structured data by law. Foreign invoices, delivery notes, claims, forms and contracts still arrive as pages, and that is where the reading is. ### Where does it run? Inside the boundary you agree before release: your cloud, a dedicated EEA tenant, a hybrid split or your own hardware. The deployment page names the four and what each one keeps inside. Paper will keep arriving. We build the workflow that reads each page, stops the wrong ones and writes the right ones once. AI Implementation covers discovery, architecture and the deployment itself.