# Ungrounded Content

Record: `arch:ungrounded-content`
Kind: anti-pattern
Layer: [Enforcement Core](https://banes-lab.com/records/layer/enforcement-core.md)
Severity: discouraged
Scope: model_governance
Canonical: https://banes-lab.com/ontology#arch-ungrounded-content

## Repair

- Refactored by: RAG_boundary, evidence_citation, claim_validation, abstain_or_disclose_uncertainty
- Detected by: answer_without_sources_when_sources_required, no_retrieval_trace, unsupported_claims, confidence_not_disclosed
- Violated by: Generate answers, classifications, plans, or decisions without evidence retrieval, source references, confidence limits, or unsupported-claim handling.

## referenced-by

- [Agentic Architecture](https://banes-lab.com/records/arch/agentic-architecture.md)