Observed arrival · 2026-11-20
The AI Agent Trials’ 80-job benchmark
A public comparison of AI agents across everyday work scenarios, from family logistics and office tasks to app-building and hospital coordination.
○Open
⊠Login
$Paid
†Ads
✦Pretty
●Pro
◎Niche
◉Human
⚑Risk
ƒJS
- For
- Readers comparing AI-agent performance on everyday tasks
- Worth noticing
- Some assignments run for weeks; one operations scenario has an AI managing a tea factory’s cash for 13 weeks.
Field notes
The homepage divides the work into eleven job families, including personal assistance, app building, customer service, hospital assistance and robot operation. It says each AI was tested as an agent rather than in a chat app, using invented households and businesses whose emails, booking sites, spreadsheets or other systems form the job setting. Some tasks span weeks; the tea-factory cash-management scenario runs for 13 weeks.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
○OpenPublic substance visible
$PaidCommerce or pricing visible
✦PrettyNotable craft visible
●ProPolished or operationally mature
◎NicheUnusually specific use
One card from the complete issue