Unverified50% confidenceSolutionExact time
采用先设计后实现的两步 Prompt 策略并控制单次 AI 任务粒度，可维持模型上下文聚焦度
1
Sources
50%
Confidence
Long-term
Relevance
7/18/2026
First Seen
Sources
Related Claims
UnverifiedPolicy enforcement for AI agents requires proactive interception, completing policy validation at the moment the AI issues a tool call request79% similarUnverifiedAI编程指令设计存在两种范式：过程驱动（Process-driven）和目标驱动（Goal-driven），目标驱动将规划权完全交给AI78% similarVerifiedAI Agent具备工具调用（Tool Use）和规划推理（Planning & Reasoning）两大核心能力，能将复杂目标自动分解为可执行的子任务序列78% similarUnverifiedAutomated jailbreaking uses another AI model to automatically generate jailbreak prompts targeting a victim model, based on the principle of adversarial prompt search.76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/556497API
curl https://kongchang.com/api/v1/knowledge/claims/556497MCP
get_claim(id=556497)