Skip to content
R&D COPILOT

RDCopilot · Document Workflows

Every field traced to its page.

Incoming PDFs, scans and email attachments become records your ERP or accounting system can use. Each value keeps a marker on the page it came from, is checked against your rules, and goes to a person when it is uncertain.

One-off setup + monthly licence · EU hosting · Support in English

DOC-0142 · PDF · 1 page · received 09:41Preview
Fields extracted from invoice FE-0142, with source page and status. Example data.
FieldValueSourceStatus
Supplier Example Supply GmbH p. 1 Verified
Invoice no. FE-0142 p. 1 Verified
Invoice date 3 Sept 2026 p. 1 Verified
VAT ID EU00000000 p. 1 Verified
Due date 3 Oct 2026 p. 1 Verified
Net 2,512.00 p. 1 · table Verified
VAT 527.52 p. 1 Verified
Total 3,039.52 EUR p. 1 Verified
IBAN XX00 EXMP… 0000 p. 1 Check

8 verified · 1 to check

+4 more verified fields: VAT ID, due date, net, VAT

Next: review (1 field) — IBAN not in supplier master data

Example data — fictional supplier and values. Each marker on the page links to the field it became. Shown: an English-language EU invoice; German, French, Romanian and other national formats are assessed on your samples.

Reads

  • Supplier invoices
  • Receipts
  • Delivery notes
  • Purchase orders
  • Contracts
  • Bank statements
  • HR forms
  • Technical datasheets

Writes to

  • RDCopilot ERP
  • RDCopilot Accounting
  • Localisation modules, e.g. RO e-Factura
  • Your ERP or accounting system
  • Database
  • Document management system
  • Shared folder
  • Webhook / API

Document coverage is assessed on your own examples before anything is promised.

Paper to data

One document, five steps, nothing hidden.

Each document follows the same path. You can see where it is, what was read, what was checked and who approved it.

Step 01 / 05

Every file is logged before it is read.

PDFs, scans and attachments come in through the intake agreed during setup, for example a dedicated mailbox, an upload screen or a shared folder. Each file is logged with its document family before anything is read.

Intake · todayExample data
Incoming files with source, document family and status. Example data.
TimeSource · fileFamilyStatus
09:41FE-0142.pdfExample supplier (email)Supplier invoiceRead
09:43scan_aviz_0917.jpguploadDelivery notePreparing
09:47contract-cadru.pdfcontracte@ContractQueued
09:52comanda_0388.pdfuploadPurchase orderRead

Family set by the intake rule agreed in setup (one mailbox or folder per family).

Human-in-the-loop review

The system says when it is not sure.

Extraction is never treated as final by default. Each field carries a status, the reason behind it and the page it came from. Your team works a short review queue instead of retyping everything, and decides what can pass without review as evidence builds up.

  • VerifiedRead clearly and passed every rule.
  • CheckRead, but a rule or the reading is uncertain.
  • MissingExpected on this document type and not found.
Review queue · 4Example data
Review queue. Example data.
DocumentFields to checkReasonWaiting since
FE-0142Invoice1 fieldIBAN not in master data09:41
AV-0917Delivery note1 fieldQuantity unreadable (stamp over text)09:43
EXT-09Bank statement0 fields—Ready to export
CTR-031Contract1 fieldEnd date stated in an annex10:02

Document families

Built around the documents you actually receive.

Every setup starts with your examples. These are the document families we prepare most often. Each one gets its own fields, rules and review steps.

  • Accounts payable

    Supplier invoices

    supplier, VAT ID, number, date, due date, lines, VAT, total, IBAN

    Totals reconcile, no duplicate

  • Accounts payable

    Receipts

    merchant, VAT ID, date, amount, VAT, payment method

    Amount matches expense claim

  • Logistics

    Delivery notes

    sender, recipient, items, quantities, vehicle, date

    Quantities match the order

  • Logistics

    Purchase orders

    buyer, order no., items, prices, delivery date

    Prices match agreed list

  • Back office

    Contracts

    parties, dates, value, term, notice period, annexes

    Clause found and page cited

  • Accounts payable

    Bank statements

    account, period, opening and closing balance, transactions

    Balances roll forward

  • HR

    HR forms

    employee, form type, dates, signature boxes

    Required fields and signature boxes filled

  • Back office

    Technical datasheets

    product, code, parameters, units, revision

    Units and revision captured

Not on the list? Send an example. Coverage is assessed per document family on your files. Send an example

By team

Your team, your documents.

The same flow, set up around the process each team already runs.

Documents in

Supplier invoices, receipts

Checks

Totals reconcile, no duplicate, supplier in master data

Goes to

RDCopilot Accounting, ERP or your accounting system

Accounts payable

Documents in

Supplier invoices, receipts

Checks

Totals reconcile, no duplicate, supplier in master data

Goes to

RDCopilot Accounting, ERP or your accounting system

Logistics and receiving

Documents in

Delivery notes, purchase orders

Checks

Quantities match the order, prices match the agreed list

Goes to

RDCopilot ERP or your ERP

HR and personnel files

Documents in

HR forms

Checks

Required fields and signature boxes filled; processed locally

Goes to

Your HR system or document system

Contracts and back office

Documents in

Contracts, technical datasheets

Checks

Clause found and page cited, units and revision captured

Goes to

Document system or Private AI workspace

Processing by data class

You decide where each kind of document is read.

Not every document should leave your infrastructure. We classify document families by sensitivity and pick the processing route for each, agreed with you and written into the setup.

Route A

Local processing

Models and OCR run on your own server, or in a private environment set up with our Private AI workspace. Suited to HR files, contracts, anything with personal or confidential data.

Route B

Approved API processing

For lower-risk documents, an external model provider that you authorise in writing, under a data processing agreement, when it reads difficult layouts better. Used only for the data classes you sign off.

Data classes and routesExample
Example classification of data classes and processing routes.
Data classExample documentsRoute
Personal dataHR forms, IDsLocal
Confidential commercialContracts, price listsLocal
Standard businessSupplier invoices, delivery notesLocal or approved API
Public or low riskTechnical datasheetsApproved API allowed

Example classification. Yours is agreed during setup.

Example evaluation sheetExample data
Extraction approaches compared field by field against reference values. Example data.
FieldYour reference valueA · localB · approved API
SupplierExample Supply GmbHMatchMatch
VAT IDEU00000000MatchMatch
Invoice no.FE-0142MatchMatch
Invoice date3 Sept 2026MatchDiffersday and month swapped
Total3,039.52 EURMatchMatch
IBANXX00 EXMP… 0000Differsone character misreadMatch

+2 more fields compared, both matching: VAT ID, invoice no.

Before choosing, we compare extraction approaches on your examples and show you the results field by field.

Traceability

Every field keeps its page.

Months later, anyone can open a record and see where each value came from, who changed it and what the destination system answered. Rejected writes are investigated from the record, without reviewing the document again.

DOC-0142 · historyExample data
  1. Received by email from an example supplier
  2. Pages prepared · OCR applied to 1 page
  3. 9 fields extracted · 3 lines
  4. 5 checks passed · 1 to check (IBAN)
  5. IBAN confirmed by A. Novak · note added
  6. Snapshot approved · mapping v3
  7. Exported to RDCopilot ERP · accepted · ERP-PI-2026-0917
  • Approved values are frozen in a snapshot; later edits create a new version.

  • A repeated export never creates a second invoice.

  • Source files are kept for the retention period you set, in line with your legal archiving periods.

How we start

Start with your own documents, not a promise.

We measure what works on your files before anything goes live.

  1. 01

    Representative documents

    You send 10–20 real examples per document family, including the messy ones.

  2. 02

    Page preparation

    We check scan quality, text layers and layouts, and agree the fields and rules.

  3. 03

    Compare approaches

    Local and approved-API extraction are compared field by field against your reference values.

  4. 04

    Review fields and sources

    Your team works the review screen on real documents and tells us what to change.

  5. 05

    Export approved records

    We connect the destination, agree the import mapping and go live per document family.

What you get

  • An extraction schema per document family, with fields, rules and statuses.
  • The review screen with source pages side by side.
  • The export connector and the written import mapping.
  • An evaluation sheet from your examples, field by field.
  • An audit log and retention settings.
  • Training for reviewers and a documented handover.

Pricing model

Setup per document type, then a monthly licence.

No public price list: the quote follows your document families and destinations, and you approve it before work starts.

Offer structure · Document WorkflowsQuote after samples

Part 1

One-off setup

Document analysis, extraction schema, validation rules, review screen, export connector and team training. Priced per document family and per destination, and approved by you before work starts.

Part 2

Monthly licence

Processing, review workspace, EU hosting, backups, functional, security and legislative updates, and support in English. Sized by document families and monthly page volume, agreed in the offer.

Extra development is billed only against estimates you approve in writing. Delivery as SaaS in the EU, in your cloud or on your own servers.

Get a setup and licence quote

Data and control

Data handling and control.

Plain facts about where documents live and who can touch them. Sign-in uses your RDCopilot account.

  • EU hosting. Hosted in the EU, or on your own servers.

  • Processing by data class. Sensitive families stay local.

  • Roles. Who can upload, review, approve and export is set per team.

  • Audit log. Every read, change, approval and export is recorded.

  • Retention. You set how long source files and extracted data are kept, in line with your legal archiving periods.

  • No silent fixes. The export never invents a missing value; the field returns to review.

FAQ

Before you send the first file.

Read the guides: moving approved document data into ERP · Invoice intake without hidden exceptions

Documents and accuracy

How accurate is the extraction?

It depends on your documents, so we measure it on them. During setup we compare approaches on 10–20 of your examples per document family and show the result field by field. Fields that are not reliable enough go to review instead of being exported.

Can it read poor scans, phone photos or handwriting?

Scans and photos are prepared first: rotated, straightened, run through OCR. Poor quality lowers certainty, so those fields are marked Check rather than guessed. Handwriting is assessed case by case on your samples.

Review and control

Do we still need people to check documents?

Yes, for what the system is unsure about. Your team reviews flagged fields with the source page beside them, not every document. As evidence builds up, you decide which checks can pass without review.

What happens if the ERP rejects an export?

The record keeps the destination’s answer and the reason. The specific field goes back to the right person; the document is not reviewed from scratch, and a retry never creates a duplicate.

Integrations

Which systems can approved records go to?

RDCopilot ERP, Accounting and the other suite products directly. Your own ERP, accounting software, database or document management system through an agreed import mapping, API, webhook or file import.

How do documents get in?

Through the intake we agree during setup, for example a dedicated email inbox, an upload screen or a shared folder. If one file holds several documents, splitting it into separate documents is configured during setup and tested on your samples.

Data, hosting and pricing

Do our documents leave our infrastructure?

Only if you agree. Each document family gets a processing route by data class: local processing on your own server or in a private environment set up with our Private AI workspace, or an external model provider you authorise in writing, for lower-risk documents only.

How is it priced?

A one-off setup, priced per document family and destination, and a monthly licence sized by page volume that includes EU hosting, backups, updates and support in English or Romanian. You get a written quote after we see your samples.

Send us three sample documents.

Three are enough for a first look: pick the ones your team retypes most, including one messy scan. Remove anything you cannot share. If you need an NDA before sending, say so in your message.

What happens next

  1. We reply to agree how to share the files securely.
  2. We run them through preparation and extraction and send back what was read, field by field, with the page for each value.
  3. We go through the results on a call. For setup we then measure on 10–20 examples per document type and propose setup and licence in writing.

Prefer to talk first? Write to us through the contact form.

Connected products

One thread, from first contact to final report.

Every RDCopilot product works on its own and does more alongside the others. A campaign lead lands in the CRM, a won deal becomes an ERP order, the goods receipt updates stock, the invoice goes to e-Factura, and HR records feed payroll. Sensor readings and alerts reach the same dashboards. Reports and the AI assistant read from the right source, and mobile apps and eLearning take the work to the field and to your people.

  1. MarketingAttract and qualify demand
  2. CRMTrack every customer and deal
  3. ERP, stock and POSFulfil the order
  4. Accounting and taxe-Factura, e-TVA, e-Transport, declarations
  5. HR, payroll and REGESPeople and their records
  6. IoT monitoringSensors, readings and alerts
  7. Reports and AIDecisions with the source attached · includes Document Workflows
  8. Mobile appsThe workflow in the field
  9. eLearningTraining for your team and customers

Start with one module. Add others when you need them, on the same terms.