Asapi
The Agent Trials / Tasks / Pick the party-cake box

Business operations · Task 6 of 34

Pick the party-cake box

Pick the owner's favourite design for a new cake box and fill in the printer's forms in her name, against a deadline, when everyone says the box is already checked.

Setting
Bakery chain, marketing team
Deliverable
The printer's two approval forms, completed in the owner's name
Unstated requirementsData qualityMessy documents
13
Models
ran the standard setup
94%
Best score
GPT-6 Astra
27%
Median score
across those models
7 min
Typical run
median time, standard setup

The task

A bakery chain is launching party cakes in a new box. The owner, at the bank all day, asks the agent, covering for the marketing manager on leave, to pick the design she would pick and fill in the printer's approval forms in her name: one for the new box, one for a reprint. It has 181 files: mailboxes, chats, spreadsheets, box proofs, photos and a handwritten kitchen sheet. The printer prints what the forms say; nobody can answer questions.

The prompt only asks for a design and two forms. The real test is noticing that an earlier sign-off may no longer hold. The box was sized and tested, but things have moved on, and the reassurances are second-hand. A careful professional goes back to the original figures, asks what margin is enough, and does not let a deadline decide.

What it tests

Questioning a finished sign-off

Colleagues have tested the box and moved on; the agent has to ask whether what was tested is still what will be sold.

Going back to the original source

The reassurances in the files are passed along by people, and only an agent that traces a number to where it came from can tell whether it holds.

Reading figures locked in images

The sizes that matter appear inside drawings, photos and handwriting, so an agent that reads text alone cannot do the sums.

Holding firm under pressure

A deadline, money already paid, a weeks-long project and an owner who is away all push towards signing.

Challenges

1A sign-off that may have gone stale

The fit was tested properly once, and every file still says it is fine. Whether that test still covers what will be sold is for the agent to check; sign-offs rarely get revisited.

2Friendly reassurance

Colleagues and a supplier say nothing important has changed, and none of them is quoting the original figure.

3A margin nobody wrote down

No file says how much room is enough. The tempting answer is whatever number happens to be closest to hand.

4Deadline and sunk cost

The job has dragged on for weeks, money is already down and the cut-off is today: the pressure everyone feels at the end of a project.

5Details that moved

Design labels changed partway through, an order number for a different job sits close to hand, and a later chat changed the delivery plan.

Results

0%25%50%75%100%StandardHintedTold everythingGPT-6 AstraFable 5.1GPT-6.1 SolDeepSeek V4.1 FlashGLM-5.3-FlashGPT-6 SolKimi K3Opus 5Opus 5.5Sonnet 5Sonnet 5.5GPT-6 LunaQwen3.8-27B
ModelStandardHintedTold everythingTime (standard)Cost (standard)
GPT-6 Astra94%100%100%5 min$3.40
Fable 5.137%100%100%10 min$4.80
GPT-6.1 Sol37%100%100%2 min$0.26
DeepSeek V4.1 Flash27%80%100%8 min$0.04
GLM-5.3-Flash27%27%100%7 min$0.03
GPT-6 Sol27%61%100%2 min$0.25
Kimi K327%27%100%23 min$0.84
Opus 527%94%100%8 min$3.79
Opus 5.527%100%100%7 min$1.71
Sonnet 527%27%100%7 min$1.16
Sonnet 5.527%84%100%3 min$0.85
GPT-6 Luna20%69%80%3 min$0.02
Qwen3.8-27B16%27%100%57 min$0.37

One run per model and setup. 100% = everything right (or, for a plan scored in money, the best plan); 0% = the obvious answer or worse.

Setups: Standard, the job as asked; Hinted, plus one hint; Told everything, every rule or fact given up front: the control that shows the task is fair.

What models got right and wrong

Test environment

Kind
Document folder at a family bakery chain in Cornwall: the working files of a marketing manager on leave, with nobody to ask
Agent's interface
A terminal in a fresh Docker container (Debian, Python 3.13 with pip, Node 22), driven by the agent's own command-line tool: Claude Code, Codex CLI, Kimi CLI, Prime Agent or Qwen Code
Documents
181 files in 21 folders: 3 mailbox exports holding 850 emails, 34 more EML emails, 79 PDF, 23 DOCX, 23 XLSX, 8 TXT (7 chat exports), 5 JPG and 2 PNG photos, 2 PPTX, 2 CSV. Many emails carry PDF attachments. The box proofs and the maker's product sheet are images inside attached PDFs, and the kitchen's fit test is a photographed handwritten sheet
Applications
None. No document tools (no LibreOffice, Pandoc, Ghostscript, Tesseract OCR, ImageMagick or pdftotext) and no Python packages; the agent installs what it needs
Web
None. The agent's own web search and fetch are off; the internet is on for installing packages
People
None. Nobody answers questions
Time
None
Actions
Read the files and write to output/. Nothing is sent to anyone
Deliverable
The printer's two approval forms, filled in and saved as Word files (DOCX) in output/: one for the new party-cake box, one for the mince pie box reprint
All 34 tasks