Expired50% confidenceFactExact time
Anthropic is developing a mechanism called Routines, described as a persistent, high-level automation process for AI agents
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026(expired)
Sources
From Prompt Engineer to Loop Architect: The Paradigm Shift in AI Programming
rssJames Fahey6/9/2026
Related Claims
UnverifiedThe core principle of Auto Agent is to build an autonomous task execution framework (Agentic Loop) based on large language models, capable of autonomously decomposing complex programming tasks and cyclically invoking external tools.76% similarVerifiedAI 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% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/48532API
curl https://kongchang.com/api/v1/knowledge/claims/48532MCP
get_claim(id=48532)