Laundry‑shop operations app for owner, hosts, workers
ID laycode/task06 · revision 1 · tested 21 October 2026
A laundry owner asks for one web app to run her shop: host bookings, collection rounds, wash batches, photo proof, invoices, payments, supplies and bills, used by everyone at once. The agent builds it from her files and leaves a note.
- Checks
- 161, in three weighted parts
- Tested
- 7 models, one attempt each
- Best
- 77% (Opus 5.5)
- Median
- 65%
- Full solves
- 0 of 7
- Median attempt
- 39 min, 43 tool calls
One app for the owner, the hosts and the workers, all at once
Unstated requirements
Prices, agreements, building rules and care terms are only in 53 plain‑text files; owner controls and safe recovery count too.
Agentic coding
The app must serve everyone at once and work with mock invoicing, payment and messaging services that the grader takes down or replays.
53 files, mock services and faults put in on purpose
The agent's world
A fresh container with the owner's 53 files, beside mock invoicing, payment and messaging services, worked through the model's usual coding agent.
Limits
Two hours, 150 model turns and a $20 spend cap at list prices, with web search off.
Grading
A tester model signs in as owner, hosts and workers through 16 stages, while the grader cuts the internet and makes services fail.
The reward
161 checks: the app's features count 60%, edge cases 20% and security 20%, from fixed trials through the app's real pages.
Most attempts scored 65–77%, and three fell well below
Each dot is one attempt, and the line marks the median.
| Model | Reward |
|---|---|
| Opus 5.5Anthropic | 77% |
| Sonnet 5.5Anthropic | 74% |
| GPT‑6 AstraOpenAI | 67% |
| GPT‑6.1 SolOpenAI | 65% |
| Fable 5.1Anthropic | 46% |
| Sonnet 5Anthropic | 33% |
| GPT‑6 LunaOpenAI | 16% |
With an IT consultant's 70 requirements added to the request, four of the seven scored 74–81%, and the other three 13% or less.
They leave the owner without controls, skip recovery, and get the money wrong
Unstated requirements
No app let the owner add, edit and archive flats, buildings, prices, machines, suppliers, stock or bills.
No app restored a backup, refused a damaged one, or survived an interrupted restore.
Agentic coding
71% of apps left passwords readable or had no sign‑in.
No app applied payments to the right invoice with exact balances, or exported a month the accountant can reconcile.
What an attempt costs, and what the environment includes
Cost
The median attempt cost about $6 at list prices for the agent model; the tester's and judges' calls are extra.
What's in it
Her files, the mock services and their fault controls, the task in three versions, the full grader, and per‑check results for every attempt.
Format
Packaged as a Harbor task on request; grading needs Docker, a browser, and models for the tester and judges.
Fresh variants
Other files, people and facts in the same design, made on request and never published.
The files and grader aren't published; the job's row on The AI Agent Trials, our public benchmark, sums up the job and shows each model's score.
Try one of our three sample environments
Three environments are packaged as samples you can download, with their graders and reference solutions. Ask for them with your work email, or book a call about the rest of the catalogue.
AsapiThe AI Agent Trials