[控场AI]
待验证50% 置信事实精确时间

Anthropic is developing a mechanism called Routines, described as a persistent, high-level automation process for AI agents

1
来源数
50%
置信度
中期 (~90 天)
时效性
2026/7/2
首次发现
有效期至：2026/9/30

来源

From Prompt Engineer to Loop Architect: The Paradigm Shift in AI Programming
rssJames Fahey2026/6/9

相关事实

待验证Auto Agent的核心原理是基于大语言模型构建自主任务执行框架（Agentic Loop），能够自主分解复杂编程任务并循环调用外部工具76% 相似已验证AI Agent基于ReAct（Reasoning + Acting）等框架，能够将复杂任务分解为多个子步骤，自主决定何时调用外部工具75% 相似

引用此条事实

Stable URI
https://kongchang.com/claim/48532
API
curl https://kongchang.com/api/v1/knowledge/claims/48532
MCP
get_claim(id=48532)