Home · Business · Operations & Logistics · Suppliers & ordering

PARTLY

As of 13 August 2026, AI can only partly estimate when a supplier will deliver your order.

Most people should hand this to a purpose-built tool.

Can you do it?

5 minutesto a draft.

30 minutesto something you’d act on.

Cost, all in£0

Skill neededchat-fluent

Who has to check ityou

What the alternative costsNo priced human alternative is supplied in the available data.

If this goes wrong: you plan around a late delivery and face a stockout, production delay or unnecessary escalation.

What to actually do

  1. Use a tool built for this

    The route this page recommends

  2. Do it yourself

    Second choice

    A chat interface, chat-fluent skill, and roughly 30 minutes until you can act on the result.

    How to actually do it

    1. Open the purchase order or ordering system and gather the order date, items, quantities, agreed lead time and required-by date.
    2. Collect the supplier's latest confirmation, dispatch notice, tracking update and any message mentioning a delay, backorder or revised date.
    3. Add comparable past deliveries from the same supplier if you have them, including the promised and actual dates.
    4. Paste the gathered information into the prompt, keeping the dates, timestamps and supplier wording intact.
    5. Ask the chatbot for the delivery windows, evidence, assumptions, confidence and supplier follow-up specified in the prompt.
    6. Compare the estimate with the latest supplier confirmation and tracking status, then record the estimate as a planning assumption rather than a confirmed delivery date.
    7. If the later window threatens your required-by date, send the suggested question to the supplier and update the order record with the reply.

    Prompt

    Estimate when this supplier is likely to deliver my order using only the information I provide. Do not invent dates, tracking events, lead times or supplier commitments. Separate confirmed facts from assumptions. Give me: 1) the most likely delivery window, 2) an earlier and later plausible window, 3) the evidence for each window, 4) the information that is missing or contradictory, 5) a confidence rating explained in plain English, and 6) the next question I should send to the supplier. Treat a supplier's latest explicit confirmation as stronger evidence than an old standard lead time, and do not treat an estimate as a promise. Order details: [paste order number, order date, items, quantities and agreed lead time]. Supplier messages and confirmations: [paste relevant emails or messages]. Dispatch and tracking information: [paste the latest status and timestamps]. Previous deliveries from this supplier: [paste comparable dates and outcomes, if available]. Our required-by date: [insert date or write none].

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

  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 see a supplier's live warehouse, transport or order-management system unless you provide an authorised data connection.
  • It cannot know that a supplier has missed an internal commitment that was never recorded in the information you supplied.
  • It cannot turn an uncertain delivery window into a reliable promise.
  • It cannot decide the operational cost of waiting, expediting, substituting stock or changing production without your business context.
  • It can give false precision when supplier messages conflict or the historical examples are not comparable.

What caps this at PARTLY: real time truth, stakes of error and judgement under ambiguity.

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
Inputs1
Verification1
Liability1
Effort delta2
Total7 / 10

The methodology and its thresholds are published in full.

FAQ

Can AI predict my supplier's delivery date?
Partly. It can estimate a delivery window from order records, supplier messages, lead times and tracking updates, but it cannot see an unreported delay or guarantee what the supplier will do.
What information does AI need to estimate a delivery date?
Give it the order date, items, quantities, agreed lead time, required-by date, latest supplier confirmation, dispatch status and tracking details. Comparable previous deliveries help, but the latest explicit supplier information matters most.
Can AI tell me if my supplier is going to be late?
It can compare the supplier's commitment with the latest evidence and flag a likely delay. You still need to confirm the position with the supplier because the model has no independent view of their stock or transport operation.
Can AI contact my supplier about a late order?
It can draft a clear follow-up message using the order information you provide. You should check the order number, dates and requested action before sending it, and use the supplier's approved communication channel.

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.