Practical governance for AI agents
How to control what AI agents can do, written for the people who deploy them.
Runtime policy, identity, guardrails, containment, audit and regulation for engineers, product managers and compliance leads. Vendor-neutral, with sources and code.
Latest articles All articles
-
A map of AI agent governance techniques
Thirteen families of controls for AI agents, where each one sits in the request path, and which risk it actually reduces.
-
Runtime policy enforcement for AI agents: tools, code and comparison
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.
-
Circuit breakers for agents that act at machine speed
A short pattern note on budgets, rate limits and automatic shutdown, with a 30-line implementation.
Featured whitepaper All whitepapers
Controlling agent actions: a reference architecture
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.
Key findings
- A single enforcement point in front of every tool call is the control that most other controls depend on; without it, logging and approvals have nothing reliable to attach to.
- Agents should hold their own identities with task-scoped, short-lived credentials. Sharing a human user's session makes actions unattributable and permissions impossible to narrow.
- Tracking whether untrusted content influenced a request, and tightening policy when it did, reduces exposure to prompt injection more than input filtering alone.
Get the next piece by email
New articles and whitepapers on controlling AI agents, with a short note on what changed in regulation and tooling. No promotions.