Codewerk.
Get a quote
Home/Blog/30,000 product texts without 30,000 hallucinations

30,000 product texts without 30,000 hallucinations

Generating catalogue copy with an LLM works — if you never let it invent a number. The pipeline we use in production.

Photo: free stock photography (Unsplash licence) — see imprint

Structured input only

Feed the model the attribute table, not a vague brief. Every fact in the output must be traceable to a field. If the model needs a value that does not exist in your PIM, the correct output is silence, not invention.

Validate the output mechanically

After generation, check that every number in the text appears in the source attributes. This one regex-level check catches the majority of hallucinations before a human ever reads them.

Humans approve, in batches

Route generated texts into a simple approval queue with the source data side by side. A product manager can approve 200 an hour when the comparison is right in front of them — and reject the odd one that reads wrong.

Do not generate what Google already has

If the manufacturer's text is already indexed on ten other shops, a rephrased version adds nothing. Generate what only you have: application notes, compatibility, what your customers actually ask before buying.

Key takeaways
  • Every fact must trace back to a PIM field.
  • Machine-check numbers before a human reads the text.
  • Generate what is unique to you, not the vendor blurb.

We do this for a living — Shopware, Node.js, React, ERP integration and automation for B2B.

Talk to an engineer

// Keep reading

Related articles

AI & Automation 9 min

AI in e-commerce: what actually works in 2026

Product descriptions, search, support triage, forecasting. Three of those pay for themselves. We separate the working from the pitching.

25 Mar 2026 Codewerk Team