Skip to content

AI explained in plain English. Read the latest articles

Automation Intermediate

AI invoice processing: get PDFs into Excel automatically

Every month you waste time retyping invoices. Here’s how AI can pull data from PDFs, what you still need to check, and what the tax office requires.

AI invoice processing: a business owner checks scanned invoices and a spreadsheet on a laptop

AI invoice processing suddenly sounds appealing when it is the end of the month, you have 23 PDFs in your inbox and you are retyping everything one by one. An AI model can read fields in an invoice, such as supplier, date, invoice number, VAT and total amount.

Still, one rule matters most: you remain responsible for your records. In this article, you will see how the process works, what to watch out for and how to build a simple version with a folder, an AI step and a spreadsheet. This is a practical form of automating with AI.

How does AI invoice processing work?

A tool spots a new PDF, an AI step reads the text and turns it into fixed fields. Then a final step writes those fields into a spreadsheet.

The route usually has three parts. First there is a starting point, also called a trigger. That can be a new file in an invoice folder.

Then comes the AI extraction. The tool pulls text from the PDF and asks AI what each part means. Finally, the automation puts the data into Google Sheets or Excel.

  • Trigger: a new invoice PDF arrives in a folder.
  • AI extraction: the text is read and turned into fields such as supplier, invoice date and total.
  • Storage: the fields are added as a new row in a spreadsheet.

There is an important difference between OCR and AI extraction. OCR recognises text in a scan or image. AI then tries to understand which amount is the total and which amount is VAT, for example.

An example route is similar to what Zapier describes: new invoice PDFs in a Google Drive folder are detected, an AI step reads the content and then rows are added in Google Sheets. Zapier describes such a route as an example for financial documentation on its own site.

Note: this is one provider’s example. In other tools, steps and menu names may be different. The idea stays the same: start with a new file, let AI read the invoice and save the fields.

You do not have to connect this to your accounts straight away. In fact, for a first version, a spreadsheet is often safer. You can see what AI fills in and fix mistakes easily before anything moves on.

Which tools can you use to read invoices automatically?

You can choose between an automation tool with an AI step, a specialist invoice reader, or the scan function in your accounting software. Which option fits depends on your goal and how much control you want to keep.

If you mainly want to learn and build a route yourself, an automation tool makes sense. Think of Zapier, Make or n8n. If you want to post invoices quickly, your accounting software may be the smarter option.

If you already use accounting software with a scan function, look there first. That route often fits your existing records better. Just check the provider’s terms and costs, because these can differ by package and may change.

If you are choosing between general automation tools, also read comparing Zapier, Make and n8n.

Option Suitable for Advantage Watch out for
Automation tool with AI step, such as Zapier, Make or n8n People who want to build a route from folder to spreadsheet Flexible and easy to test with a small set of invoices You need to set up checks, privacy and storage properly yourself
Specialist invoice reader People who mainly want to read invoice fields without building much themselves Focused on invoices and often clearer for this one task Check carefully what happens to your data
Scan function in accounting software People who want to process invoices directly in their accounts Fits your existing records You still need to check invoice numbers, VAT and amounts
Manual paste into ChatGPT People who want to try a few invoices without automation Quick way to test whether AI understands the fields It is still manual work and you need to be extra careful with privacy

Whichever tool you choose, start small. Test first with a few old invoices. See whether the fields land correctly in your sheet and whether the output is easy to check.

What does it cost? That varies by provider and may change. So always check the pricing page and terms of the tool you want to use. Do not treat costs as fixed internally unless you have checked them with the provider yourself.

AI invoice processing in 5 steps: how do you build it?

You create a folder, start an automation when new files appear, let AI read the invoice, write the data to a sheet and then check it. That gives you a first version without changing your whole accounts process right away.

The goal is not for AI to do your bookkeeping on its own. The goal is to reduce the retyping. You stay in control of the result.

  1. Create a fixed folder. For example, use one folder for purchase invoices from this year. Put only invoice PDFs there that you want to process.
  2. Create an automation that starts with a new file in the folder. The tool then checks whether a new PDF has arrived.
  3. Add an AI step. Let the tool pull text from the PDF and ask AI to return fixed fields.
  4. Write the fields to a spreadsheet. Create columns for supplier, invoice date, invoice number, amount excluding VAT, VAT amount, total, VAT rate and check.
  5. Check the result. Set the status to no or unchecked first. Only change that status after you have checked it.

Use fixed field names. That keeps your spreadsheet tidy and stops each invoice from coming in slightly differently. Do not let AI write freely either, but ask for a fixed structure.

A useful prompt is this:

JSON is a fixed text format with field names and values. Many automation tools can turn such an output into columns more easily. If you do not fully understand JSON yet, that is fine. The important thing is that the tool gets the same fields for every invoice.

Before you go live, this checklist is useful:

  • Test with ten invoices from a previous month.
  • Check that each PDF really stays in your folder.
  • Add a column for the status, for example checked.
  • Set up a formula check for amount excluding VAT plus VAT equals total.
  • Read the privacy settings and terms of your tool.

The exact menu names differ by tool. So always follow the help pages of the provider you choose. The idea stays the same: file in, AI extraction, row in your sheet.

Practical example: AI invoice processing for Marloes

Marloes is an example of what such a simple route can look like. She does not use AI as an accountant, but as a helper to get PDFs into a spreadsheet faster.

Marloes is a self-employed graphic designer in Utrecht. Each month she receives about 20 purchase invoices as PDFs by email. They are for software, print work and office costs, for example.

  1. Create a folder. Marloes creates a folder in Google Drive called Purchase invoices 2026. She saves every invoice PDF she wants to process in that folder.
  2. Start with a new file in the folder. Then she creates a route in an automation tool with this start: new file in folder. That can be in a tool such as Zapier, Make or n8n.
  3. Add an AI step. That step pulls the text from the PDF and uses this prompt: You receive the text of an invoice. Return only JSON with these fields: supplier, invoice_date (YYYY-MM-DD), invoice_number, amount_ex_vat, vat_amount, total, vat_rate. If a detail is not clear, fill in “unknown” and do not guess. Text: [invoice_text]
  4. Add a row in Google Sheets. The sheet gets columns for supplier, invoice date, invoice number, amount excluding VAT, VAT amount, total and VAT rate.
  5. Set check to no by default. There is also an extra Checked column, which starts at no by default. Marloes only changes that after she has reviewed the row.

The expected result is simple. Each PDF becomes one row in the sheet with six to seven fields. Marloes then reviews those rows at a fixed time.

This example does not prove that every invoice will always be processed correctly. Invoices can vary a lot. So test with your own invoices, especially if you have scans, credit notes or invoices in another currency.

Here too, menu names differ by tool. Follow the help pages of the provider you use and check that your version supports the same steps.

Can you store invoices digitally and let AI read them?

Yes, scanning and digital storage are allowed under conditions. The retention period is 7 years, and for data about property 10 years.

The tax office says you may keep invoices and receipts digitally if it is an accurate and complete version of the original. Authenticity features must also be stored. The digital records must be checkable within a reasonable time according to the tax office.

The retention period is 7 years. For data about property, 10 years applies. The tax office also says the 7 years start when the data is no longer current on a page about record-keeping duties.

So do not just throw away your PDFs because the data is in Excel. A spreadsheet row does not replace the invoice. The spreadsheet is useful for overview, but your records must remain checkable. Store the original PDFs or a correct and complete digital copy in an organised way.

Also pay attention to privacy. Invoices can contain names, addresses and sometimes other personal data. In that case, the GDPR applies, the privacy law for personal data.

So check whether you need a data processing agreement. Also check whether data is used to train AI models. Some tools have servers outside the EU, so read what the provider says about that.

If you want to take this further, also read using AI safely. Especially with business invoices, it is sensible not to upload files to a personal account without thinking it through.

For Belgian readers, retention periods and rules may be different. Check with the Belgian Ministry of Finance and ask your accountant what applies in your situation.

How reliable is AI at reading amounts and VAT?

AI usually works better with clear PDFs than with messy scans. Still, mistakes can happen with scans, credit notes and invoices with several VAT rates.

An AI model reads text and then chooses which fields belong to it. That often works well if the invoice is neatly laid out. But AI does not understand your accounts the way you do.

A common risk is that AI fills in something that sounds logical but is wrong. That is called a hallucination. Read more about that risk in the article about AI hallucinations.

That is why you need to build checks into your process. For example, add an extra column with a formula check. It compares amount excluding VAT plus VAT with the total.

  • Red flag: the total does not match the sum.
  • Red flag: the invoice number is marked as unknown.
  • Red flag: the VAT amount is missing even though VAT is shown on the invoice.
  • Red flag: a credit note is treated as a normal invoice.

Also use a sample check. At the start, check every invoice. As your process becomes more stable, you can move to a fixed weekly check, but keep the status column.

A simple Checked column helps a lot. Set the default value to no. Only after your own check do you change it to yes.

Rompslomp, as an accounting provider, points out that you remain responsible for invoice numbers, VAT, retention duties and customer data, even if you use AI in an article about AI and invoices. So use AI as help, not as the final check.

What mistakes do people often make when automating invoices?

The biggest mistakes do not come from the technology, but from too much trust and too little checking. A few fixed rules can prevent a lot of trouble.

See these mistakes as your basic list before you go live. Go through them with every new automation.

  • Blindly trusting the extracted amounts. Solution: add a formula check column and do a weekly sample check.
  • Letting AI guess when data is missing. Solution: tell AI in your prompt to fill in unknown if something is not clear.
  • Putting invoices with customer data into a free or unclear tool. Solution: check privacy settings, data training and the data processing agreement.
  • Keeping only the extracted result and deleting the original PDF. Solution: store the PDFs in an organised way, because the original or correct digital version belongs in your records.
  • Leaving out credit notes and invoices in other currencies. Solution: add fields for type, such as invoice or credit note, and currency.

An extra tip is to keep your folder tidy. Put only files in it that really need to be processed. That stops quotes, delivery notes or old test files from ending up in your spreadsheet.

What does this mean for you as an employee or entrepreneur?

An employee saves retyping time, but first needs to check what is allowed internally. An entrepreneur can keep records faster, but remains responsible.

If you work for an organisation, ask about the policy for AI tools. Sometimes you may only use approved software. That makes sense, because invoices can contain data about customers, suppliers and employees.

If you are an entrepreneur, you can start small. Put the route alongside your existing process. Only when you know the results are easy to check should you use the sheet as a fixed part of your records.

Frequently asked questions

Can ChatGPT read my invoices?

Yes, you can paste or upload text or a PDF. Without automation, though, it remains manual work, and you need to be careful with privacy.

Is it safe to put invoices into AI tools?

That depends on the tool and the settings. Check data processing, use for training and whether there is a data processing agreement.

Do I have to keep the original paper invoice?

Not if you meet the tax office conditions for digital storage. The digital version must be accurate, complete and checkable. Authenticity features must also be stored.

How long do I need to keep invoices?

In the Netherlands, it is usually 7 years. For data about property, 10 years applies. The 7 years start when the data is no longer current.

Is this free?

Prices vary by provider and may change. So always check the site of the provider you want to use.

Can I use this with Excel instead of Google Sheets?

Yes, often you can. It depends on the automation tool and the connections the provider supports. The principle stays the same: read the PDF, create fields and add a row.

The best next step is to start small: take ten invoices from last month, build the route from the practical example and check all the results. Only then choose your permanent tool, for example with help from comparing Zapier, Make and n8n.

Was this article helpful?

New articles every day

Follow AIzine and never miss an article

We publish three new articles about AI every day. Follow us on Instagram or Facebook to see them in your feed.