Topic starter
05/07/2026 6:52 pm
TL;DR: AI security has moved beyond model testing into runtime defense as organisations push AI into production, including agentic AI systems, according to TROJ.AI. Build-time review still matters, but the decisive question is whether security teams can govern live model behaviour, tool use, and deployment exposure together.
Editorial analysis by NHI Mgmt Group, based on content published by TROJ.AI: “When AI Became the Target: An Interview with James Stewart, Co-Founder and CTO of TrojAI”.
Key questions
Q: What breaks when AI risk assessment stops at model testing?
A: You miss the non-technical risks that usually decide whether the system is safe to deploy.
Q: Why do AI governance programs need runtime enforcement for agentic workloads?
A: Agentic workloads can take actions autonomously, which makes delayed oversight too late to prevent exposure.
Q: How should organisations combine build-time and runtime AI controls?
A: Treat build-time testing and runtime defense as complementary controls.
Practitioner guidance
- Map AI systems to runtime control boundaries Inventory which deployed AI applications can call tools, reach data, or influence downstream workflows, then document the control boundary for each one.
- Separate build-time testing from live monitoring Keep red teaming, pre-release evaluation, and in-production telemetry as distinct controls with different owners and escalation paths.
- Define permissions for agentic systems explicitly Treat agentic AI as a runtime actor with scoped tool access, data access, and execution limits.
Bottom line: AI security is no longer just a pre-release model-testing problem because production systems create new runtime exposure.
Explore further
View Full Forum → | NHI Foundation Course → | Our Services → | Read the full analysis →
05/07/2026 7:12 pm
Runtime defense is now the control plane that matters most for enterprise AI. Once AI moves into production, model quality alone stops being a sufficient security signal. The operational question becomes what the system can access, invoke, or influence while it is live, especially in environments where AI is wired into business processes. Security leaders should treat runtime behaviour as the primary risk surface, because that is where safe design meets messy reality.
A question worth separating out:
Q: How should security teams govern agentic AI as it moves into production?
A: Security teams should govern agentic AI as a class of non-human identity, not as a generic application feature. That means assigning ownership, scoping permissions tightly, logging every tool action, and revoking access on a defined lifecycle. Production rollout should require clear approval points for high-risk actions and continuous monitoring for drift.
👉 Read our full editorial: AI security is moving from model testing to runtime defense