Home · Business · Operations & Logistics · Inventory & stock

PARTLY

As of 13 August 2026, AI can only partly create warehouse picking lists.

This still needs a person who signs their name to it.

Can you do it?

15 minutesto a draft.

1 hourto something you’d act on.

Cost, all in£0

Skill neededpower-user

Who has to check ita colleague

What the alternative costsNanonets is an AI document-processing tool that extracts data from invoices, receipts and forms.

If this goes wrong, staff pick the wrong items or quantities, causing rework, delayed dispatches, stock discrepancies and possible customer complaints.

What to actually do

  1. 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.

  2. Use a tool built for this

    Second choice
  3. Do it yourself

    The distant third

    A chat interface, power-user skill, and roughly 1 hour until you can act on the result.

    How to actually do it

    1. Open your current order system and export the unfulfilled orders, including order number, SKU, description, quantity, customer reference and any batch or expiry requirement.
    2. Open your stock or warehouse management system and export the current available quantity for each SKU, keeping the SKU format unchanged.
    3. Export the bin or location list and any current warehouse rules for zones, batches, expiry dates, priority orders and partial picks.
    4. Paste the three exports and the warehouse rules into the prompt, then ask the model to produce the pickable lines and separate exceptions.
    5. Paste the drafted table into a spreadsheet and compare every SKU, quantity, order number and location against the latest warehouse-system exports.
    6. Ask a warehouse colleague to check the exceptions, live stock and any batch or expiry decisions, then correct the spreadsheet rather than accepting an unverified suggestion.
    7. Send the approved picking list to the authorised warehouse process and retain the exception list so unresolved lines are not picked by mistake.

    Prompt

    Create a warehouse picking list from the order data, stock data and bin-location data below. Use only the supplied facts and do not invent SKUs, quantities, locations, stock levels or substitutions. Preserve each order number and customer reference. Group the list by picking route or bin location if the location data supports that, and include SKU, product description, quantity, bin location, order number and any batch or expiry information supplied. Separate the result into: 1) pickable lines, 2) lines with insufficient or missing stock, 3) lines with missing or conflicting location data, and 4) lines needing a human decision. Do not combine different SKUs. Flag duplicate orders and duplicate lines. Show the source order number beside every picked line. Return a plain table that can be pasted into a spreadsheet, followed by a short exception list. Do not mark any line as ready for dispatch. Before finalising, state which fields were missing or ambiguous.
    
    Order data:
    [PASTE CURRENT ORDER EXPORT]
    
    Stock data:
    [PASTE CURRENT STOCK EXPORT]
    
    Bin-location data:
    [PASTE CURRENT BIN-LOCATION EXPORT]
    
    Additional warehouse rules:
    [PASTE RULES FOR BATCHES, EXPIRY, PRIORITY, ZONES OR PARTIAL PICKS]

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

What it gets wrong

  • AI cannot see live stock, bin changes, damaged goods or items already picked unless those facts are included in the data you provide.
  • AI cannot reliably resolve ambiguous substitutions, partial picks, batch selection or expiry rules that your warehouse has not stated.
  • AI cannot guarantee that a spreadsheet export matches the warehouse system at the moment staff start picking.
  • AI cannot take responsibility for wrong picks, stock discrepancies or delayed dispatches.
  • A clean-looking list can hide a duplicated order or stale location, so a colleague still has to approve it.

What caps this at PARTLY: real time truth, verification cost 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

FAQ

Can ChatGPT make a picking list?
Yes, it can format supplied order, stock and location data into a picking list. It cannot fetch or guarantee live warehouse data, so a colleague must compare the result with the current warehouse system before picking.
Can AI create a picking list from an Excel spreadsheet?
Yes, if the spreadsheet contains clear order, SKU, quantity and location fields. Ask the model to preserve order numbers, flag missing stock and separate ambiguous lines instead of guessing.
Can AI update warehouse picking lists automatically?
Not from a standalone chat unless you build an approved connection to the systems holding current orders and stock. Without that connection, you must provide a fresh export each time and check that it is still current.
Is it safe to use AI for warehouse picking?
It is suitable for drafting and organising a list, not for unreviewed release to pickers. Wrong quantities, locations or substitutions can create stock errors and delayed customer orders, so an authorised colleague should approve the final list.

Nearby answers

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.