Notifications
Clear all
Topic starter
19/08/2026 3:37 pm
TL;DR: Agentic AI systems fail through distributed decisions, tool calls, and handoffs, so evaluation and monitoring designed for predictive models often misread where the failure actually started, according to Fiddler's analysis. The practical lesson is that measurability, structured prompts, and layered guardrails are design decisions, not retrofits, because debugging without traceable behaviour leaves teams blind.
NHIMG editorial — based on content published by Fiddler: Agent Measurability Starts Before You Build
Questions worth separating out
Q: How should security teams govern AI agents that can access enterprise systems?
A: Security teams should govern AI agents as non-human identities with explicit ownership, scoped privileges, and continuous monitoring.
Q: Why do agentic AI systems need different monitoring from traditional ML models?
A: Agentic systems create a sequence of decisions, not just a single prediction, so aggregate metrics often hide the root cause of a failure.
Q: What breaks when agent workflows are not structured for inspection?
A: Teams lose the ability to map a production issue back to a specific instruction, transition, or tool call.
Practitioner guidance
- Define evaluation rubrics before agent buildout Write success criteria at the conversation, session, and task level before any scoring begins.
- Make agent workflows traceable by design Model prompts, phases, and transition conditions as inspectable structures so production failures can be mapped to a specific step.
- Measure guardrails as separate controls Test input screening, output filtering, and post-action checks independently, then validate how the layers behave together under realistic domain shift.
What's in the full article
Fiddler's full blog covers the operational detail this post intentionally leaves for the source:
- The specific rubric design sequence used to calibrate human reviewers before automated scoring begins
- Examples of how Fiddler structures prompts and transition conditions for better inspection and debugging
- The layered guardrail approach, including how input, output, and post-action checks are tuned separately
- The AI Explained session context that expands on evaluation, monitoring, and production failure handling
👉 Read Fiddler's analysis of why agent measurability must start before build →
Agent measurability before build: are your controls ready?
Explore further
19/08/2026 4:17 pm
Measurability debt is now an AI governance issue, not a tooling issue. Agent systems create their own form of control debt when teams build behaviour before they define how it will be measured. That makes later assurance fragile, because the evidence needed for review was never captured. In identity terms, the system already had action authority before governance had visibility, which is exactly the kind of boundary failure NHI programmes must avoid.
A question worth separating out:
Q: Who is accountable when an AI agent makes a risky decision?
A: Accountability should rest with the organisation that authorised the agent, the human owner of the workflow, and the control process that allowed the behaviour. If an agent can act independently, the programme must preserve attribution, action logs, and policy decisions so audit and remediation are possible after the event.
👉 Read our full editorial: Agent measurability must be designed before deployment
