Skip to content

Yuki document recognition is getting less accurate, more manual rework.

Yuki OCR learns per vendor and per admin. Pollution from half-trained variants, low scan quality or new invoice templates from existing vendors drops the accuracy.

Try this first

  1. 1Check the top 10 problem vendors, in our experience 80 percent of errors come from a handful.
  2. 2Open the vendor card per supplier and verify VAT number, IBAN and default ledger account, Yuki recognises much better with these set.
  3. 3Force a re-check by re-submitting a few correctly booked invoices, that resets the learning layer for that vendor.
  4. 4Disallow low-resolution scans (under 200 dpi) and skewed phone uploads via WhatsApp, OCR stumbles on skew.
  5. 5Open a ticket with Yuki with example document ids if the score stays low, they have tooling to tune matchers per admin.

When to bring us in

For an audit of your Yuki admin and rules, we can make it actionable within half a day.

See also

None of the above fits?

Describe your situation below. We pass your input plus the steps you already saw to our AI and return tailored next-step advice. If it's too risky to DIY, we'll say so.

Who are you?

For the AI question we need your email and company, so we can follow up if the AI gets stuck, and to prevent abuse.

Limited to 2 questions per hour and 5 per day, kept lean so the AI stays useful. For more, contacting us directly works better for you and us.

Or skip the DIY entirely

Our Managed IT clients do not look these things up. One point of contact, a fixed monthly price, resolved within working hours.