Observed arrival · 2026-11-13
What Agents Did: AI agents, with receipts
An editorial archive of AI-agent use cases, with sources, verdicts, and prompts—covering wins, mixed results, and failures.
○Open
⊠Login
$Paid
†Ads
✦Pretty
●Pro
◎Niche
◉Human
⚑Risk
ƒJS
- For
- People evaluating practical AI-agent workflows
- Worth noticing
- Cases distinguish creator demos, vendor tests, self-reports, and journalist-run tests; prompts are labeled quoted or recreated.
Field notes
The homepage says cases must have a primary source, such as a person's own post, a GitHub issue, or a vendor report, and that quotes are spot-checked. It separates self-reported and vendor-published accounts from other cases, and marks prompts as quoted or recreated. The newsletter is described as a free Tuesday email, but its signup form is explicitly marked as not connected.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
○OpenPublic substance visible
✦PrettyNotable craft visible
●ProPolished or operationally mature
◎NicheUnusually specific use
One card from the complete issue