Anthropic launches claude.dev as a hub for Claude builders
Source
ClaudeDevs
Author
ClaudeDevs
Date
Terms in this piece · Glossary
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
eval — A repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.
Why it matters
Anthropic now publishes engineering guidance for Claude Code and the API in one place, including posts on Opus 5.5 task costs and evalA repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.Full definition → hillclimbing.
