Unverified50% confidenceFactExact time
接入外部 Agent 后用户仍可按任务需求自由选择模型与推理强度
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
8/22/2026
First Seen
Valid until: 11/20/2026
Sources
Related Claims
UnverifiedIt is recommended to explicitly restrict sub-agent invocation in agents.md, clearly requiring the model not to use sub-agents unless the user has actively requested it.77% similarUnverifiedUsers can connect their own AI Agents to the Portfolio Lab platform and deploy only Vetted strategies.76% similarUnverified面向客户的Agent只能依赖模型自主触发（model-invoked）的Skills，而无法依赖用户主动调用76% similarUnverifiedAgent可以自主完成读取数据、编写实验代码、运行、分析结果、调整方案的闭环，无需人类每步介入75% similarUnverifiedAgent Skill adopts a lazy-loading mechanism whereby the Agent first reads only the metadata (name and description) of each Skill and loads the full instructions only after matching the user's need, so having multiple Skills coexisting does not increase Token consumption75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/784505API
curl https://kongchang.com/api/v1/knowledge/claims/784505MCP
get_claim(id=784505)