Topic starter
11/11/2026 5:57 pm
TL;DR: The finding, according to Query, is that agents can look confident while consulting only a fraction of the relevant security data and still stop. Security operations then inherit a hidden completeness gap, because the investigation appears finished even when key sources were never queried.
Editorial analysis by NHI Mgmt Group, based on content published by Query: “What I learned testing AI agents against real security data”.
Key questions
Q: What signs show an AI agent has under-queried a security estate?
A: An AI agent has under-queried a security estate when it produces a neat conclusion from too few sources, skips obvious control planes, or asks no follow-up queries after finding thin evidence.
Q: How should teams handle AI investigations that stop on partial evidence?
A: Treat partial evidence as a failed investigation, not a finished one.
Practitioner guidance
- Define source-completeness thresholds Set a minimum percentage of required sources that must be queried for each investigation type before an agent can close the case.
- Validate zero-result handling Test how the agent behaves when a source returns no rows because of formatting, mapping or query-shape mismatch rather than true absence.
- Instrument query depth and follow-up rates Track how many sources the agent touches, how many it revisits and whether shallow one-pass searches are replacing deeper investigation.
Bottom line: AI agents can appear reliable while consulting only a fraction of the evidence needed for a security decision.
Glossary terms: Federated Query Execution, Normalization Layer, Confident Incompleteness
Explore further
View Full Forum → | NHI Foundation Course → | Our Services → | Read the full analysis →
11/11/2026 6:06 pm
Confidently incomplete is the right failure name for this class of agent error. The dangerous outcome is not an obviously bad answer, but a polished answer built on only part of the estate. That shifts the control problem from detection of wrong conclusions to detection of missing evidence. For identity and security teams, the governance question is whether an agent can prove it consulted the sources that matter before it closes the case.
A few things that frame the scale:
- Systems with least-privileged AI access had a 17% incident rate vs 76% for over-privileged systems. Organisations failing to scope AI access properly are 4.5x more likely to experience a security incident, according to the 2026 Infrastructure Identity Survey.
A question worth separating out:
Q: What signs show an AI agent has under-queried a security estate?
A: An AI agent has under-queried a security estate when it produces a neat conclusion from too few sources, skips obvious control planes, or asks no follow-up queries after finding thin evidence. Other signs are narrow tool use, repeated reliance on one dataset, and no attempt to reconcile conflicting logs or permissions.
👉 Read our full editorial: AI agents can sound complete while missing security evidence