Real Agent Cases

Order groceries from a 16-item list with OpenAI Operator

Source date:
Last verified:
Method:
How we verify

Evidence: Article or interviewA newsletter, journalist or interview account of what happened.

Outcome

Operator misread parts of a 16-item grocery list and added only 13 items to the cart even after corrections; the author concluded it wasn't ready for real use.

Agent

OpenAI Operator

Prompt Recreated prompt

The source did not publish its exact prompt. This one is our reconstruction from what the source describes.

Here is my shopping list. Place an online grocery order for the items that have checkmarks.

Source

https://www.understandingai.org/p/computer-use-agents-seem-like-a-dead

By Timothy B. Lee · Published Jun 26, 2025 · Added Oct 15, 2026 · Last verified Oct 15, 2026

  • Order groceries from H-E-B with ChatGPT agent (access denied)Improved promptEvidence: Screenshots or logsFailure

    The poster tried to order groceries from H-E-B in Austin with ChatGPT agent, but it failed because access was denied.

    ChatGPT agent · Shopping · Source date:

  • Fill an online grocery cart from a handwritten list with ChatGPT agentImproved promptEvidence: Article or interviewPartial

    ChatGPT agent transcribed 15 of 16 items from a photographed shopping list (missing onions), found the nearest Harris Teeter and added them to the cart; a safety monitor first blocked the Kroger login, but after the user said they'd log in themselves and entered the password, it ordered the groceries.

    ChatGPT agent · Shopping · Source date:

  • Given access to Instacart and told to prep an order from the poster's history and current sales, ChatGPT agent picked items with reasoning the poster found oddly generic ("cereal, which is on sale and a usual part of groceries").

    ChatGPT agent · Shopping · Source date: