# Model Inference

> The ability to run a trained model on validated input at runtime and return a checked prediction or generation.

Record: `architecture:model-inference`
Kind: capability
Layer: [Correctness Core](https://banes-lab.com/records/layer/correctness-core.md)
Severity: contextual
Scope: service, model serving
Aliases: Runtime Prediction/Generation
Canonical: https://banes-lab.com/ontology#architecture-model-inference

Listed in [Architecture principles](https://banes-lab.com/api/records/architecture.md), after [Model Evaluation](https://banes-lab.com/records/architecture/model-evaluation.md) and before [Retrieval-Augmented Generation (RAG)](https://banes-lab.com/records/architecture/retrieval-augmented-generation.md).

## Repair

- Refactored by: Add Inference Service, Add Adapter/Contract
- Detected by: raw model calls in business logic
- Violated by: inference without validation/observability/fallback
- Measured by: [latency](https://banes-lab.com/records/architecture/latency.md), error rate, output quality
- Enforced by: serving standards

## Requires

- [Model Artifact](https://banes-lab.com/records/lexicon/model-artifact.md)
- [Input/Output Contract](https://banes-lab.com/records/lexicon/input-output-contract.md)

## Reinforces

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

## Conflicts with

- [Training-Time-Only Model Logic](https://banes-lab.com/records/lexicon/training-time-only-model-logic.md)

## In tension with

- [Latency/Cost](https://banes-lab.com/records/lexicon/latency-cost.md)

## Tensions

- [Model Inference / Latency/Cost](https://banes-lab.com/records/tension/latency-cost-model-inference.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)

## Required by

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

## Linked from

- [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)
