Unverified50% confidenceFactExact time
In Agenthof's demonstration, a real model is given the Agent's actual capabilities as tools and decides round by round what to call; when the Agent oversteps, what stops it is the door, not a script; model-driven operation does not require adding new door types.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/15/2026
First Seen
Valid until: 1/13/2027
Sources
Related Entities
Related Claims
UnverifiedA bare large model can only decide to call a certain tool but does not actually execute the tool, whereas an Agent can truly execute tool calls and return results.77% similarUnverifiedThe Agentic loop means the model decides its next action each round based on the current context, the control flow is produced by the model, and the path is unpredictable; Agenthof governs by constraining the door of each call rather than constraining the model's thinking.76% similarVerifiedAgent mode means the model is no longer a passive responder but an active task agent that plans and executes tasks step by step.76% similarUnverifiedAgenthof splits the system into two completely independent programs: agenthof is the governance engine, responsible for apply, run, audit, and investigate, never embedding the Agent and never deciding how the Agent thinks; the Agent is a separate program (a small LangChain Agent in the repository), agenthof calls it over a socket and drives it with the model door, tool door, execution door, and spawn door.76% similarVerifiedAgent的核心公式为：Agent = 大模型 + 工具调用 + 自主决策能力75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1038805API
curl https://kongchang.com/api/v1/knowledge/claims/1038805MCP
get_claim(id=1038805)