Engineering at Anthropic: Inside the team building reliable AI systems
Anthropicの技術記事
table:infobox
記事タイトル
投稿日 YYYY-MM-DD
記事の種類 記事には何が書かれているか、一言で表す
概要 この記事には何が書かれているか
Code execution with MCP: building more efficient AI agents
Building agents with the Claude Agent SDK (2025-09-29)
より上位感があるなmiyamonz.icon
Effective context engineering for AI agents (2025-09-29)
A postmortem of three recent issues
Equipping agents for the real world with Agent Skills
Writing effective tools for agents — with agents
Desktop Extensions: One-click MCP server installation for Claude Desktop (2025-06-26)
How we built our multi-agent research system
こっちのほうが古いが、effective toolsのほうが粒度が小さいし先にそっちをやる方が良さそうだmiyamonz.icon
Claude Code: Best practices for agentic coding (2025-04-18)
The "think" tool: Enabling Claude to stop and think in complex tool use situations (2025-03-20)
Raising the bar on SWE-bench Verified with Claude 3.5 Sonnet (2025-01-06)
Building effective agents (2024-12-19)
Introducing Contextual Retrieval (2024-09-19)
multi-agent
agent (skill)
tool
ただしtoolはどこからでも使える
こういう階層関係があるな
skillの中でtool useがあるから、最下層はtoolだろう
subagentsはClaude Codeだけだが、skillと立ち位置は近いか？