Observed arrival · 2026-10-21
TriedAgents puts AI-agent claims to a ground-truth test
The site re-runs popular AI-agent use cases with exact prompts, checks the results against ground truth, and rates how much account access each task requires.
○Open
⊠Login
$Paid
†Ads
✦Pretty
●Pro
◎Niche
◉Human
⚑Risk
ƒJS
- For
- People evaluating AI agents before giving them account access
- Worth noticing
- Its access scale runs from L0 public-web-only tasks to L4 actions that spend money or delete data.
Field notes
The case list spans travel, research, home and daily life, money, and shopping, with filters for both verdict and account access. Individual entries include run dates and elapsed times; for example, the visible International Space Station check compares a public tracker with an orbit calculation based on published elements.
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
ƒJavaScriptBrowser-side code central
One card from the complete issue