Observability and audit
Tracing agent decisions and keeping records that stand up to review.
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.
Articles
-
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.