Blog
-
Getting email and PDF receipts into the same system
Digital-original receipts need no OCR and cause more duplicates than photos do. How to ingest them without ending up with three records per purchase.
-
Why the tax amount is harder to extract than the total
Every receipt shows a total. Not every receipt shows its tax as a number you can read. Six reasons the tax field fails, and what to do instead.
-
Trialling a receipt app on your own data
Vendor accuracy claims are unfalsifiable. A two-week trial on your own awkward receipts, scored per field, gives you a number that means something.
-
Approval rules for a small team's expenses
Approval asks whether the money should have been spent. Review asks whether the data is right. Conflating them makes both worse.
-
What a confidence score actually tells you
A confidence score is a model's estimate of its own reading, not the odds it is right. What it measures, and how to set a threshold on it.
-
Scanning receipts in a foreign currency
The receipt shows one amount and your statement shows another. Which to record, why they differ, and what to capture while you are still abroad.
-
What to expect from an accounting software integration
Integrations move data, not judgement. Six questions to ask before you connect two systems, and the failure modes each one prevents.
-
Where receipt scanning fits in a bookkeeping workflow
Scanning is one step in a five-step chain, and its output is a draft entry rather than a finished one. Knowing the difference prevents a lot of mess.
-
What a small business expense tracker actually needs to do
Six capabilities decide whether expense tracking sticks. Most feature lists are longer than that and lighter on the ones that matter.
-
Designing a review queue people actually use
Automated capture still needs human eyes, but only on the right items. What belongs in a review queue, and what should never reach one.
-
What to do about expenses with no receipt
A missing receipt is a record-keeping problem with a partial solution: document it now, from memory, while the memory is still worth something.
-
Matching receipts to card transactions
The bank feed knows how many expenses happened. Matching receipts against it is the check that finds missing evidence while it can still be found.
-
Duplicate receipts are the most common data problem
Most receipt data quality issues are not misread amounts. They are the same expense entered twice, and the same expense in two forms.
-
OCR is not data extraction
Reading the characters on a receipt and knowing which of them is the total are two different problems. Confusing them explains most disappointment.
-
What automated expense reports actually automate
The tedious part of an expense report was never the form. It was collecting evidence, and that is the part automation genuinely removes.
-
What AI expense categorisation gets right and wrong
Automatic categorisation is excellent at repetition and poor at intent. The split explains which expenses you can automate and which need a human.
-
How to scan receipts with your phone properly
The photo decides whether the scan works. Six habits that fix most capture failures, and the two that matter more than all the others.
-
How accurate is AI receipt scanning?
Accurate enough that reviewing is faster than typing, and never accurate enough to skip reviewing. Which fields you can trust, and which you cannot.
-
How AI receipt scanning works, end to end
A receipt goes from a photo to a categorised line in your books in five stages. Here is what happens at each one, and where each one breaks.
-
Going paperless without losing anything
The risk in going paperless is not the scanning. It is the gap between destroying the paper and having a digital copy you have actually verified.
-
Vendor names are the hidden data quality problem
One supplier appears under five different names across your records. Nothing looks broken, and every vendor-level report is quietly wrong.
-
When you need line items and when the total is enough
Line-item extraction is the least reliable part of receipt scanning. Four situations justify the trouble, and most expenses are not among them.
-
Which file format to keep receipts in
Keep the original capture, in a format anything can open, exportable in bulk. Which formats qualify, and which quietly tie your records to one app.
-
What a receipt app can see
Receipts are detailed personal records: where you were, when, with whom, and what you bought. Worth knowing what you hand over, and to whom.
-
A quarterly check on your own expense data
Individually correct entries can add up to wrong reports. Six aggregate checks that find the errors no per-receipt review will ever catch.