# Ungrounded Content

> A defect in which the model produces answers or decisions without retrieved evidence or disclosed uncertainty.

Record: `architecture: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#architecture-ungrounded-content

Listed in [Architecture principles](https://banes-lab.com/api/records/architecture.md), after [Prompt Sprawl](https://banes-lab.com/records/architecture/prompt-sprawl.md) and before [Model Version Ambiguity](https://banes-lab.com/records/architecture/model-version-ambiguity.md).

## 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.
- Measured by: answers without a source where one is required
- Enforced by: retrieval evaluation, claim validation against the retrieved sources

## Contracts

- [Agent Creator Kernel](https://banes-lab.com/records/algorithms/agent-creator-kernel.md)

## Severity

- [discouraged](https://banes-lab.com/records/vocabulary/severity-discouraged.md)

## Category

- [Anti-patterns](https://banes-lab.com/records/architecture-category/anti-patterns.md)

## Force

- [Model governance](https://banes-lab.com/records/force/model-governance.md)

## Negated by

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

## Linked from

- [It looked right](https://banes-lab.com/disciplined-methodology/verify/it-looked-right.md)
- [Agents as executed contracts](https://banes-lab.com/disciplined-methodology/collaborate/agents-as-executed-contracts.md)
- [The author is probabilistic](https://banes-lab.com/software-architecture/scale/the-author-is-probabilistic.md)
- [Anti-patterns](https://banes-lab.com/ontology/principles/architecture-category-anti-patterns.md)
- [Model Architecture](https://banes-lab.com/ontology/principles/architecture-category-model-architecture.md)
- [Agent creation](https://banes-lab.com/ontology/algorithms/algorithms-domain-agent-creation.md)
- [Severity levels](https://banes-lab.com/ontology/schema/the-vocabulary-severity.md)
- [The forces](https://banes-lab.com/ontology/schema/the-forces.md)