Anthropic and OpenAI release AI agent development guide
The 115-article collection covers the full lifecycle of agent systems, from design to production. The guide systematizes approaches to building agents, focusing on the Model Context Protocol (MCP) standard for integrating external data and tools.
The guide details architectural patterns for workflow orchestration, task handover, security, and autonomy control. It also covers tools like Claude Code and OpenAI Codex, including testing with Evals, context management, sandboxing for secure code execution, and creating agent self-improvement loops.
Related stories
- Amodei warns the UN Security Council about AI risk
- Claude Marketplace opens its shelf to outside builders
- Opus 5.5 costs less and answers old agent code with 400s
- Fears of AI apocalypse crashed into Anthropic's $2T IPO
- Ex-Anthropic engineer's exit post passed 170 million views
- A November IPO buys Anthropic time to show Q3 numbers
Comments
No comments yet. Be the first.
Join the conversation
Sign in with Google to leave a comment. Your name and avatar come from your Google profile, and the comment appears after moderation.