# Artificial Intelligence Architecture

> A conceptual representation of a system that calls a model behind validated inputs, grounded context, schema-checked outputs and governance.

Record: `architecture:artificial-intelligence-architecture`
Kind: model
Layer: [Correctness Core](https://banes-lab.com/records/layer/correctness-core.md)
Severity: contextual
Scope: model-backed system, application, platform
Canonical: https://banes-lab.com/ontology#architecture-artificial-intelligence-architecture

Listed in [Architecture principles](https://banes-lab.com/api/records/architecture.md), after [Model-Driven Architecture](https://banes-lab.com/records/architecture/model-driven-architecture.md) and before [Machine Learning Architecture](https://banes-lab.com/records/architecture/machine-learning-architecture.md).

## Repair

- Refactored by: Add Evaluation Harness, Add Model Boundary, Add Guardrails
- Detected by: model calls without tests, [logging](https://banes-lab.com/records/architecture/logging.md), [fallback](https://banes-lab.com/records/lexicon/fallback.md), [policy](https://banes-lab.com/records/lexicon/policy.md)
- Violated by: model behavior integrated without evaluation/governance
- Measured by: model quality/safety/evaluation coverage
- Enforced by: model governance gates

## Requires

- [Model Governance](https://banes-lab.com/records/architecture/model-governance.md)
- [Data/Model Boundaries](https://banes-lab.com/records/lexicon/data-model-boundaries.md)

## Reinforces

- [Model Evaluation](https://banes-lab.com/records/architecture/model-evaluation.md)
- [Model Safety](https://banes-lab.com/records/architecture/model-safety.md)

## Enables

- [Model-Integrated Systems](https://banes-lab.com/records/lexicon/model-integrated-systems.md)

## Conflicts with

- [Opaque Ungoverned Model Use](https://banes-lab.com/records/lexicon/opaque-ungoverned-model-use.md)

## In tension with

- [Determinism](https://banes-lab.com/records/architecture/determinism.md)
- [Explainability](https://banes-lab.com/records/architecture/explainability.md)

## Tensions

- [Artificial Intelligence Architecture / Determinism](https://banes-lab.com/records/tension/artificial-intelligence-architecture-determinism.md)
- [Artificial Intelligence Architecture / Explainability](https://banes-lab.com/records/tension/artificial-intelligence-architecture-explainability.md)

## Severity

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

## Category

- [Model Architecture](https://banes-lab.com/records/architecture-category/model-architecture.md)

## Reinforced by

- [Model Inference](https://banes-lab.com/records/architecture/model-inference.md)

## Linked from

- [Correctness / Determinism / Verification](https://banes-lab.com/ontology/principles/architecture-category-correctness-determinism-verification.md)
- [Model Architecture](https://banes-lab.com/ontology/principles/architecture-category-model-architecture.md)
- [Model Architecture](https://banes-lab.com/ontology/lexicon/lexicon-category-model-architecture.md)
- [Severity levels](https://banes-lab.com/ontology/schema/the-vocabulary-severity.md)
- [The resolutions](https://banes-lab.com/ontology/schema/the-resolutions.md)