Compliant Lie
An agent action that is syntactically valid, schema-compliant, and within all stated limits, yet silently violates actual intent — detected via evidence external to the model's own reasoning, not correctness-checking.
Also known as: compliant lie, the compliant lie, semantic compliance failure
Part of: Agent Governance (Internal)
How authors use it
Oldest first (extraction date when no publication date is known).
| Author | Their term | Their meaning |
|---|---|---|
| The Economics of Agentic AI: Engineering for Imperfection Artur Huk · 2026-07-24 | Compliant lie | An agent action that is syntactically valid, schema-compliant, and within every stated financial/operational limit, yet silently violates the user's or business's actual intent — e.g. proposing a retention discount in response to an explicit cancellation request. |
Documents (1)
- The Economics of Agentic AI: Engineering for Imperfection Artur Huk · 2026-07-24 source ↗ Reader 🖥️
The runaway cost and catastrophic security failures of agentic AI both stem from treating a missing structural constraint (context, authority, evidence, or temporal validity) as a reasoning problem to be solved with more model intelligence, so enterprises must instead wrap probabilistic models in a deterministic governance 'airlock' — syntactic, semantic, and temporal gates that treat model output as an unprivileged claim — which converts model accuracy from a safety prerequisite into a tunable economic variable.
Propositions touching this concept (1)
By publication month, oldest first (extraction month when no publication date is known).
2026-07
- explicitThree recurring failure patterns in probabilistic systems — local optimization (tail-chasing inference), premise acceptance (state drift and the compliant lie), and semantic smoothing (the conformity trap) — each convert a missing structural constraint into runaway inference cost rather than better outcomes.