Observed arrival · 2026-10-18
What Agents Pick
A public scoreboard comparing the tools Claude Code models choose when a prompt doesn’t name a vendor.
○Open
⊠Login
$Paid
†Ads
✦Pretty
●Pro
◎Niche
◉Human
⚑Risk
ƒJS
- For
- Developers choosing defaults for coding-agent projects
- Worth noticing
- Auth results are tool-free across all three models, while no ORM leader exceeds a 50% share.
Field notes
The comparison is organized around ten categories, from database and deployment to caching and monitoring. Its tables include top-pick shares and runner-ups, plus agreement or split indicators; the visible ORM results show SQLAlchemy at 50% for each model, with Drizzle ORM as a runner-up. The homepage links to methodology and About pages, but their contents are not included in this extract.
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