Observed arrival · 2026-10-08
AI Evaluation Field Guide
A 26-pattern guide to evaluating AI systems, with filters for different roles and links to practical evaluation tools.
○Open
⊠Login
$Paid
†Ads
✦Pretty
●Pro
◎Niche
◉Human
⚑Risk
ƒJS
- For
- People building, buying, or designing with AI
- Worth noticing
- Filters sort patterns by building, buying, or designing, while individual entries can be added to a Quick brief.
Field notes
Readers can filter the patterns by building, buying, or designing, and browse five numbered sections. The visible entries distinguish measurement problems from test-design problems, including contaminated training data, adaptive overfitting, and graders that may favor their own model. A search control and per-pattern add actions sit alongside a Quick brief; the page also links to a claim checker, design rubric, and readiness review.
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