<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Agent Governance Notes</title><description>Independent, vendor-neutral writing on how to control what AI agents can do: runtime policy, identity, guardrails, containment, audit and regulation.</description><link>https://agent-governance-site.pages.dev/</link><language>en-gb</language><item><title>A map of AI agent governance techniques</title><link>https://agent-governance-site.pages.dev/articles/map-of-ai-agent-governance-techniques/</link><guid isPermaLink="true">https://agent-governance-site.pages.dev/articles/map-of-ai-agent-governance-techniques/</guid><description>Thirteen families of controls for AI agents, where each one sits in the request path, and which risk it actually reduces.</description><pubDate>Tue, 10 Nov 2026 00:00:00 GMT</pubDate><category>runtime-policy-enforcement</category><category>agent-identity-and-access</category><category>prompt-injection-defence</category><category>regulation-and-standards</category><author>Your Name</author></item><item><title>Runtime policy enforcement for AI agents: tools, code and comparison</title><link>https://agent-governance-site.pages.dev/articles/runtime-policy-enforcement-for-ai-agents/</link><guid isPermaLink="true">https://agent-governance-site.pages.dev/articles/runtime-policy-enforcement-for-ai-agents/</guid><description>How to put a deterministic policy gate in front of every tool call, with working code in Python, Rego and Cedar and a comparison of approaches.</description><pubDate>Tue, 03 Nov 2026 00:00:00 GMT</pubDate><category>runtime-policy-enforcement</category><category>human-in-the-loop</category><category>observability-and-audit</category><author>Your Name</author></item><item><title>Whitepaper: Controlling agent actions: a reference architecture</title><link>https://agent-governance-site.pages.dev/whitepapers/controlling-agent-actions-reference-architecture/</link><guid isPermaLink="true">https://agent-governance-site.pages.dev/whitepapers/controlling-agent-actions-reference-architecture/</guid><description>A vendor-neutral reference architecture for deciding, enforcing and recording what AI agents may do, with a maturity model and a mapping to the EU AI Act, ISO/IEC 42001 and NIST AI RMF.</description><pubDate>Fri, 30 Oct 2026 00:00:00 GMT</pubDate><category>runtime-policy-enforcement</category><category>agent-identity-and-access</category><category>observability-and-audit</category><category>regulation-and-standards</category><author>Your Name</author></item><item><title>Circuit breakers for agents that act at machine speed</title><link>https://agent-governance-site.pages.dev/articles/circuit-breakers-for-agents/</link><guid isPermaLink="true">https://agent-governance-site.pages.dev/articles/circuit-breakers-for-agents/</guid><description>A short pattern note on budgets, rate limits and automatic shutdown, with a 30-line implementation.</description><pubDate>Tue, 20 Oct 2026 00:00:00 GMT</pubDate><category>containment-and-circuit-breakers</category><category>observability-and-audit</category><author>Your Name</author></item></channel></rss>