Blog · Published · Updated
Automating receipt matching for company cards
Short answer
Receipt matching automation links photos of receipts to company card transactions by amount, date and merchant, shows gaps and unclear matches, and writes the employee a specific question. A photo sent again does not create a second expense. At Syntalith the automation costs from €3,000 net, and with 1,500 card transactions a month at 3 minutes each it pays back in 1.5 months.
How we workDetails ↓
- 01Call30 minutes with an engineer, free
- 02PrototypeA working system on your process and data, free
- 03ImplementationTarget and fixed price in the contract; 50% at signing
- 04Acceptance50% once the agreed target is met
- net for the automation of one process, build paid once
- from €3,000
- from signing the contract to acceptance
- 2–6 weeks
- free prototype on your cases
- €0
We belong to the OpenAI and Anthropic partner programmes and learn through their official courses. What this means ↓
Author: Syntalith · 3 min read
Statistics
Expenses and AI: statistics 2026
1.5 mo.
payback of a €3,000 automation at 1,500 card transactions a month: €2,618 of work today, €666 with checking and the model. Scenario.
30.7%
According to Eurostat (2025), 30.7% of EU companies paid for cloud software for finance and accounting.
Source: Eurostat, digital economy and society statistics, enterprises (2025) ↗
−87%
According to Anthropic (2025), AI cuts the time of a task on invoices, memos and other documents by an estimated 87%.
Source: Anthropic, Estimating AI productivity gains (2025) ↗
14–56%
According to Anthropic (2025), studies with a control group found smaller time savings, from 14% to 56%.
Source: Anthropic, Estimating AI productivity gains (2025) ↗
90%
According to the European Commission (2026), 90% of companies using AI say that people take the decisions, and 2% of decisions are fully automated.
Source: European Commission, Flash Eurobarometer 578 (2026) ↗
Figures checked: 22 October 2026
Receipt matching: the receipt is in the inbox and still shows as missing
An employee pays with a company card for two purchases from the same merchant during a trip. After returning, she sends a photo of one receipt without saying which purchase it belongs to. The person preparing the expense report sees two transactions and one document, and both purchases still show as missing on the statement. She searches email for the receipt, compares amounts and writes to the employee.
The automation reads the amount, date and merchant from the receipt and compares them with the transactions. When the amount matches one of them, it links the document to that purchase. When it matches both or neither, it asks the employee about the specific purchase with its date and amount. After the clarification the receipt stays with the transaction, and the same photo sent again leads to the document already recognised. The dates and currencies from both sources are kept, because a difference does not always rule out a link, and it must not vanish through a default conversion.
- Two purchases from the same merchant with one receipt
- A purchase in a foreign currency with a receipt in the local currency
- The same receipt photo sent again
- An illegible receipt to clarify
Rules handle known links and the list of gaps. AI helps read data from the photo, and an illegible document needs a clarification with the employee.
What automated receipt matching costs and when it pays back
- Today
- 1,500 card transactions × 3 min = 75 h (€2,618)
- With the system, a person checks the output in 25% of the time
- €655
- Model, 1 call per case, Claude Sonnet 5.5
- €11
- Cost of one case
- €1.75 today, €0.44 with the system
- Saving
- €1,952 a month
Payback of €3,000
1.5 months
The volume, the time and the checking share are the scenario's assumptions. €34.90 an hour is the EU average hourly labour cost for 2025 according to Eurostat. Model: 2,500 input tokens and 300 output tokens per call at Anthropic's rates, converted at the ECB rate of 1.1205 USD per euro on 22 October 2026.
The count covers the work around each case: searching, reading, writing and handing over. What remains is the time to check the result, 25% of today's work in the scenario. Before the quote we measure both times on 20 to 100 cases the team has already handled, in a free test that takes 5 working days.
Check the matching in your current tool
Expensify links a scanned receipt to a card transaction when the matching conditions are met, and explains where duplicate expenses come from. If your company uses such a tool, start with how it handles documents and exceptions: routing photos to the right place may bring the benefit by itself. An automation makes sense when receipts arrive by email and messaging apps and transactions come from several banks.
An expense tool with card matching
configuration and a channel for sending photos
a licence
A few dozen transactions a month
a spreadsheet and reminders
no build
Hundreds of transactions, several banks, receipts in email
a matching automation with questions
from €3,000
Where to start
The first scope covers one source of transactions and one channel for documents. The client names the required materials and the people who clarify unclear cases. We build this kind of system as part of our AI automations. For the free process review, a description of one case from the last few weeks and the tools it went through is enough. You do not need to send confidential documents, and you receive a written plan within 2 working days.
Worked example · Scenario
How we count the payback: AI in finance
We run the same count for your expenses in the free process review.
€2,094
a month for preparing 20 reports
Payback: 1.7 mo.
3 hours to collect the data and prepare a report and checking in 15% of the old time are our assumptions. €34.90 an hour is the EU average hourly labour cost for 2025 according to Eurostat, for companies with 10 or more employees. Model cost: checking the commentary in our reporting system (about €0.0002) plus compiling the data (Claude Sonnet 5.5, about 30,000 + 2,000 tokens), at the ECB rate of 1.1205 USD per euro on 22 October 2026.
See the full calculation →