Invoice documents ready for a person to check.
This working demonstration takes an invoice attachment from email, files the original in OneDrive and prepares an Excel register row. The extracted figures sit alongside the document for a person to check. It does not approve payments or demonstrate an integration with accounting software.
Relevant to: Businesses whose invoices arrive as email attachments and are saved, renamed and retyped into a spreadsheet by hand.
Studio demonstration · The walkthrough shows representative behaviour. Explore the implementation
What this means for your team
- Before
- Someone saves each invoice and copies its details into a register.
- With the workflow
- The workflow prepares the filing and register entry, leaving the financial checks and approval with your team.
What happens when it’s wrong
The original document remains available for checking. A sender check advises rather than approves, and payment decisions stay with a person.
See the behaviour
Guided workflow demonstration
Follow one representative item from business input to reviewable output. The sequence explains the work; it does not represent processing speed.
Walkthrough ready.
Synthetic invoice attachment
Sample data- File
- invoice-2026-0142.pdf
- Supplier
- Avon Office Supplies Ltd
- Invoice total
- £486.00 GBP
- Sender
- accounts@avon-office.example
- 01
Detect the invoice
Check whether the attachment appears to be an invoice before extraction.
- 02
Extract the declared schema
Read the ten agreed invoice fields into a fixed structure.
- 03
Check the sender
Compare the sender with the business allow-list and add a warning if unfamiliar.
- 04
Store the original
Save the source document to a dated OneDrive path.
- 05
Prepare the register row
Combine extracted fields with traceability fields for Excel.
- 06
Flag for review
Surface warnings and missing fields before anybody relies on the record.
Read the complete walkthrough as text
Input: File: invoice-2026-0142.pdf; Supplier: Avon Office Supplies Ltd; Invoice total: £486.00 GBP; Sender: accounts@avon-office.example.
- Detect the invoice. Check whether the attachment appears to be an invoice before extraction.
- Extract the declared schema. Read the ten agreed invoice fields into a fixed structure.
- Check the sender. Compare the sender with the business allow-list and add a warning if unfamiliar.
- Store the original. Save the source document to a dated OneDrive path.
- Prepare the register row. Combine extracted fields with traceability fields for Excel.
- Flag for review. Surface warnings and missing fields before anybody relies on the record.
Output: Invoice: 2026-0142 · Avon Office Supplies Ltd · £486.00 GBP; Stored document: Invoices/2026/09/invoice-2026-0142.pdf; Review note: Confirm extracted total and supplier before approval.
Human control: The workflow prepares a reviewable record; payment approval remains entirely human.
Guided walkthrough using representative sample data. It demonstrates the workflow’s behaviour; it is not an accuracy benchmark.
Full evaluation report
The build details, available evidence, safeguards and limitations follow. How we evaluate.
The problem
Invoices often arrive as email attachments before someone saves the file, reads the figures and retypes them into a tracking spreadsheet.
The work is repetitive, but extracted totals, supplier details and payment information still need a clear route for human checking before they are relied upon.
How the work was done before
Each invoice is handled by opening the email, saving the attachment somewhere findable, renaming it, reading the figures off the document and typing them into a spreadsheet row.
The errors this produces are quiet ones: a transposed total, a missing tax line, a file saved where nobody looks for it again.
What we built
The workflow first checks whether an attachment appears to be an invoice. Only documents that pass continue to the more detailed extraction step. Text PDFs are read directly; photographs and scans use image understanding.
It extracts ten fields from the document: invoice number, supplier, supplier email, invoice date, due date, line items, subtotal, tax, total and currency. The source file is stored in a dated OneDrive path, and a row is appended to an Excel register. That row is fifteen columns wide: the ten extracted values plus five record fields the workflow supplies itself — sender address, received date, file name, OneDrive path and any review note.
The sender address is compared with an allow-list. An unfamiliar sender does not silently reject the invoice; it adds a warning to the Notes field so a person can review it alongside the extracted data.
What we have measured
This report documents the build and its safeguards. The guided walkthrough above illustrates behaviour rather than measuring accuracy.
The documented system and walkthrough show the implementation. A project-specific evaluation establishes performance against the tasks, examples and acceptance criteria agreed for your business. The evaluation methodology sets out what we hold ourselves to before publishing a number.
How it fits together
The architecture, for readers who want the technical shape after seeing the business behaviour above.
- Type
- In-house build
- Runs on
- n8n Cloud
- Reads
- PDF, PNG, JPG
- Writes to
- OneDrive + Excel 365
- Fields extracted
- 10 per invoice
Where this approach could help
This approach can reduce invoice data entry and improve document filing while keeping payment approval, exceptions and unfamiliar suppliers with the finance team.
Related service
Document & Order Processing
Extract details from emails and PDFs, flag exceptions and prepare records for your existing business software.Related service
Workflow automation
Take the copying, retyping and chasing out of a process, while keeping a clear route for the cases that need a person.