Notifications
Clear all
Topic starter
01/07/2026 2:05 am
TL;DR: A governed semantic layer gives LLMs and agents certified definitions, metrics, relationships and rules so they reason from business meaning instead of guessing, and a KU Leuven test cited by Collibra found accuracy improved from 62% to 92% with governed context in the loop. The governance issue is no longer data access alone, but whether AI can act on meaning that is trusted, current and authorised.
NHIMG editorial — based on content published by Collibra: The semantic layer for AI: Why LLMs and agents need business context to be trustworthy
By the numbers:
- The failure rate dropped from 38.5% to 7.7% when governed context was present.
Questions worth separating out
Q: How should security teams govern AI systems that rely on business definitions at runtime?
A: Security teams should require certified definitions, approved metrics and policy metadata to be delivered together at runtime.
Q: Why do semantic layers matter for AI agent governance?
A: Semantic layers matter because agents do not just read data, they use it to decide and act.
Q: What breaks when AI uses raw data without governed context?
A: Without governed context, the system can choose the wrong definition, calculate the wrong metric or use data in an unapproved way.
Practitioner guidance
- Certify the business terms AI is allowed to use Start with the handful of metrics and definitions that drive decisions, then assign ownership, approval and review for each one.
- Bind meaning to policy, lineage and quality signals Do not let semantic definitions travel alone.
- Limit agent action to governed context paths Require AI agents to resolve definitions and approved data sources through a controlled context service before they can query, summarize or act on business information.
What's in the full article
Collibra's full article covers the operational detail this post intentionally leaves for the source:
- The article's worked examples for turning business terms into machine-readable definitions that agents can consume.
- The side-by-side comparison between semantic layer and context layer, including lineage, quality, ownership and policy.
- The runtime grounding flow for LLMs, agents and text-to-SQL systems when they need certified business meaning.
- The implementation framing for building an AI-ready semantic layer through governed, open standards.
👉 Read Collibra's analysis of the semantic layer for AI and business context →
Semantic layers for AI: what IAM and data teams need to know?
Explore further
01/07/2026 2:26 am
Semantic meaning is now an identity control, not just a data-governance concern. Once LLMs and agents consume business meaning at runtime, the question becomes who certifies the meaning that drives action. That moves semantic layers out of the BI silo and into the control stack that governs who or what may act on behalf of the organisation. Practitioners should treat governed meaning as part of the identity surface, not a sidecar to analytics.
A few things that frame the scale:
- In an independent test at KU Leuven, the same model on the same data answered correctly 92% of the time with a governed context layer in the loop and 62% without it, according to LLMjacking: How Attackers Hijack AI Using Compromised NHIs.
- The failure rate dropped from 38.5% to 7.7% when governed context was present, a reminder that runtime meaning changes outcomes, not just reporting quality.
A question worth separating out:
Q: Should organisations treat semantic governance as part of identity governance?
A: Yes. Once AI systems can retrieve, interpret and act on business information, the meaning they use becomes part of the control surface. Identity governance has to cover not only who can access data, but which meanings, metrics and actions are authorised for that identity at runtime.
👉 Read our full editorial: Semantic layers for AI: why trust depends on governed meaning
