9 posts
聂·基层运行逻辑 · Agent Skill：基于聂辉华《基层中国的运行逻辑》的方法论工具箱（不含原书全文）
YAO = Yielding AI Outcomes. A rigorous engineering, evaluation, governance, and portability system for reusable agent skills.
Don't be the 40%. A production-ready blueprint for governing autonomous AI agents in IT operations — with executable policies, typed tool co...
Securing AI Agents in Production
A living world where agents exist as participants alongside NPCs, internal actors, real service APIs, budgets, policies, and consequences.
Productized LLM Wiki pattern + typed pack registry + proposal-only governance — UNESCO Memory of the World Triple Anchor
Pre-execution policy engine for AI agents. Every tool call checked before execution.
Preloop is the Governance Layer for AI agents: MCP firewall, model gateway, human approvals, cost tracking, event-driven flows
Remote MCP server for Tandem docs, install guides, SDKs, workflows, and agent setup help.
