Home · Business · Operations & Logistics · Suppliers & ordering
As of 13 August 2026, AI can extract product details from supplier catalogues.
This still needs a person who signs their name to it.
Can you do it?
5 minutesto a draft.
30 minutesto something you’d act on.
Cost, all in£0
Skill needednone
Who has to check ityou
What the alternative costsA purpose-built document-processing alternative is Nanonets, which extracts data from invoices, receipts and forms.
If this goes wrong: a missed or altered product detail leads to the wrong item, quantity or price being ordered and the mistake reaches your purchasing process.
What to actually do
Hand it to a person
The route this page recommends
A person who owns the outcome does this end to end, worth it when the failure is dear.
Use a tool built for this
Second choiceDo it yourself
The distant thirdA chat interface, no skill needed, and roughly 30 minutes until you can act on the result.
How to actually do it
- Open the supplier catalogue as a searchable PDF or scan it at readable quality, and gather any accompanying price lists, product-code sheets or ordering instructions.
- Write down the exact fields your purchasing or stock system needs, such as product code, description, pack size, price, unit, minimum order quantity and availability.
- Paste the prompt into an AI chat or document-extraction tool, attach the catalogue and replace the two bracketed slots with your required output format and files.
- Ask the tool to process the catalogue in sections if the file is too large, keeping the same column headings and including the source page for every row.
- Export the result to a spreadsheet and compare product codes, pack sizes, prices and units against the original catalogue pages, starting with every row marked "needs checking".
- Resolve unclear or conflicting rows with the supplier, then send only the checked rows into your purchasing or stock system.
Prompt
Extract product details from the catalogue I provide. Return one row per product in a table with these columns: product name, supplier product code, brand, description, pack size, unit of measure, price, currency, minimum order quantity, availability, catalogue page and any notes. Preserve the wording and numbers from the source exactly where possible. Do not guess, calculate, normalise or fill gaps. If a field is missing, write "not stated". If a scan, table or value is unclear, write "needs checking" and identify the page and field. Keep prices separate from pack sizes and do not treat a case price as a unit price. After the table, list every row marked "needs checking" and every product with conflicting details. Catalogue: [attach or paste the catalogue]. Required output format: [CSV, spreadsheet-style table or other format].
Open it prefilled in ChatGPT or Claude, or copy it into Gemini, which takes no prefill link.
What it gets wrong
- AI cannot know whether a price is per item, case, pallet or another unit unless the catalogue states it clearly.
- AI cannot establish that a catalogue is current or that an item is still available without a reliable supplier update.
- AI can misread small print, scanned tables, product codes and columns that continue across pages.
- AI cannot decide whether two differently named products are substitutes or whether a product meets your operational requirements.
- You still carry the consequences of an incorrect order, even when the extraction came from an AI tool.
Even on a YES, the friction has a name: verification cost, real time truth and stakes of error.
How we scored this
Five axes, each scored nought to two by hand: ten means AI carries the task cleanly, and the thresholds that turn a total into YES, PARTLY or NO are published in the methodology. Each axis name links to its definition.
| Axis | Score (0–2) |
|---|---|
| Output | 2 |
| Inputs | 2 |
| Verification | 1 |
| Liability | 1 |
| Effort delta | 2 |
| Total | 8 / 10 |
The methodology and its thresholds are published in full.
FAQ
- Can ChatGPT extract data from a PDF catalogue?
- Yes. It can turn catalogue text and tables into a structured list, but you must check product codes, prices, pack sizes and units against the original pages.
- Can AI extract product prices from supplier catalogues?
- Yes, when the prices are readable and their units are clear. It cannot safely decide whether a figure applies per item, case or another pack, so check the surrounding catalogue wording.
- Can AI extract product details from a scanned catalogue?
- Usually, if the scan is clear enough for text recognition. Small print, skewed pages, columns and faint tables can produce missing or altered values, so ask for page references and check unclear rows.
- What is the best AI tool for extracting data from catalogues?
- Parseur is a suitable purpose-built option because it extracts data from documents, emails and PDFs. A general chatbot can also handle a small catalogue, while a larger catalogue benefits from a repeatable document-extraction workflow.
Nearby answers
- Can AI find a packaging supplier for my business?YES
- Can AI find alternative suppliers for a product I buy?PARTLY
- Can AI recommend the best supplier for my business?PARTLY
- Can AI write a complaint to a supplier about a bad order?YES
- Can AI check reviews of a UK supplier?YES
- Can AI compare wholesale prices from UK suppliers?YES
Assessed by gpt-5.6-luna (gpt-5.6-luna) on 2026-08-13, second-checked by an independent model. Wrong somewhere? Email [email protected] and it gets re-checked.
The newsletter
AI news, new answers and product picks, straight to your inbox.