Home · Business · Operations & Logistics · Suppliers & ordering

YES

As of 13 August 2026, AI can extract order details from supplier emails.

Most people should do this themselves; the prompt is on this page.

Can you do it?

5 minutesto a draft.

15 minutesto something you’d act on.

Cost, all in£0

Skill neededchat-fluent

Who has to check ityou

What the alternative costsParseur is a purpose-built AI document extraction tool that pulls data out of emails and PDFs.

If this goes wrong: a quantity, product code or delivery date is copied incorrectly and you correct it against the supplier email before placing or updating the order.

What to actually do

  1. Do it yourself

    The route this page recommends

    A chat interface, chat-fluent skill, and roughly 15 minutes until you can act on the result.

    How to actually do it

    1. Open the supplier email, its order confirmation and any attached PDF or spreadsheet, and save the original files so you can compare them later.
    2. Copy the complete email thread and the readable contents of the attachments into the prompt at the marked slot, including the sender, dates, subject, order references and delivery details.
    3. Paste the prompt into a chatbot and ask it to produce the extraction without changing product codes, quantities, prices or dates.
    4. Copy the resulting table into your ordering or stock system, keeping the original email and attachments linked to the record.
    5. Compare every table row with the source email and attachments, especially product codes, quantities, prices, VAT wording, delivery dates and addresses.
    6. Resolve every item marked CHECK CONFLICT or not stated with the supplier or your internal order record before sending, receiving or paying for the order.

    Prompt

    Extract the order details from the supplier email and any attached order document below. Return one row per product in a plain table with these columns: supplier, purchase order number, supplier order number, order date, product code, product description, quantity, unit, unit price, currency, VAT treatment if stated, requested delivery date, delivery address, delivery method, and notes. Copy values exactly as written. Do not guess, normalise, calculate or fill gaps. If a field is missing, write "not stated". If the email and attachment conflict, show both values in the notes column and mark the row "CHECK CONFLICT". Preserve product codes, decimal places and leading zeroes. After the table, list every unclear, conflicting or unusually formatted item that needs checking against the original email or supplier. Supplier email and attachments: [PASTE EMAIL TEXT AND DOCUMENT CONTENT HERE]

    Open it prefilled in ChatGPT or Claude, or copy it into Gemini, which takes no prefill link.

  2. Use a tool built for this

    Second choice

  3. Hand it to a person

    The distant third

    A person who owns the outcome does this end to end, worth it when the failure is dear.

What it gets wrong

  • It cannot retrieve emails from your mailbox unless you provide the message or use a connected workflow.
  • It cannot know which of several supplier messages is the valid latest instruction without a clear thread and ordering process.
  • It cannot resolve contradictory quantities, prices or delivery dates by contacting the supplier.
  • It can reproduce a supplier's typo or ambiguous wording, so the source still needs checking before the order is actioned.

Even on a YES, the friction has a name: private data access and context depth.

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.

AxisScore (0–2)
Output2
Inputs2
Verification2
Liability2
Effort delta2
Total10 / 10

The methodology and its thresholds are published in full.

FAQ

Can ChatGPT extract order details from emails?
Yes. Give it the complete supplier email and any attachment text, then ask for a fixed table and tell it not to guess missing or conflicting values. Check the table against the original before updating stock or placing the order.
What order details can AI extract from a supplier email?
It can extract details such as product codes, descriptions, quantities, prices, currency, order references, delivery dates, addresses and notes when they are stated clearly. It should mark missing or conflicting information rather than inventing an answer.
Can AI read supplier email attachments?
A chatbot may be able to read an uploaded PDF, spreadsheet or document, but you need to provide the file and check that its contents were read correctly. Scanned documents, tables and poor formatting can produce missed or misplaced values.
Is it safe to use AI to process supplier orders?
It is suitable for preparing a draft record when you keep the original email and verify the extracted fields. Do not let an unchecked extraction trigger a purchase, delivery change or payment, because you remain responsible for the operational decision.

Nearby answers

All Suppliers & ordering rulings

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.