Topic starter
02/08/2026 11:23 am
TL;DR: LLM agents fail in ways single-turn chatbots do not, with Openlayer citing a 41% failure rate on complex multi-step tasks and runtime thresholds for groundedness and toxicity that must be enforced before tool calls complete. The governance problem is no longer output review, but session-level control, auditability, and policy enforcement inside the execution loop.
Editorial analysis by NHI Mgmt Group, based on content published by Openlayer: “Production Agent Governance Guide (June 2026)”.
By the numbers:
- LLM agents fail 41% of the time on complex multi-step tasks, according to Openlayer.
- Runtime guardrails block unsafe outputs when groundedness drops below 0.85 or toxicity exceeds 0.15, according to Openlayer.
Key questions
Q: How should security teams govern AI agents that call internal tools from Kubernetes?
A: They should separate runtime containment from identity governance.
Q: Why do AI teammates create more risk than read-only chatbots?
A: Because they can move from advice to action.
Q: What signals show that an AI agent is operating outside its intended purpose?
A: Look for mismatches across identity, data, model behaviour, posture, and environment.
Practitioner guidance
- Implement step-level policy enforcement Check every tool call before it completes, and block actions that exceed declared scope or violate runtime policy thresholds.
- Set runtime guardrails for output quality Enforce groundedness and toxicity thresholds at the API boundary so unsafe responses never reach users or downstream tools.
- Instrument full-session observability Capture the sequence of prompts, tool calls, intermediate outputs, and state changes so auditors can reconstruct the decision chain.
Bottom line: Agent governance fails when teams keep treating multi-step systems like chatbots, because the harmful action often happens before any final response is reviewed.
Explore further
View Full Forum → | NHI Foundation Course → | Our Services → | Read the full analysis →
02/08/2026 12:40 pm
Step-level governance is now the control boundary for production agents. The article makes clear that output review is too late once an agent can call tools and mutate state mid-session. Governance has to move from the response layer to the execution layer, where policy decisions can stop a bad action before it compounds. For practitioners, that means treating each tool call as an authorization event, not just an observability event.
A few things that frame the scale:
- Only 44% of organisations have implemented any policies to manage their AI agents, despite 92% agreeing that governing AI agents is critical to enterprise security, according to the 2026 Infrastructure Identity Survey.
- AI-related credential leaks surged 81.5% year-over-year in 2025, with the surrounding AI infrastructure leaking 5x faster than core LLM providers, according to the State of Secrets Sprawl 2026.
A question worth separating out:
Q: Which controls should teams use to prove EU AI Act compliance for agents?
A: Teams should rely on runtime policy enforcement, detailed decision logs, and defined human-approval points for higher-risk actions. Those controls create evidence that the system did not merely have a rule on paper but actually applied it when the agent acted. That evidence is what auditors and assurance teams will expect.
👉 Read our full editorial: AI agent governance in production demands step-level controls