# Evaluation Suite

> A technique for scoring model output against a fixed set of cases on every change to the model, prompt or data.

Record: `lexicon:evaluation-suite`
Kind: technique
Layer: [Correctness Core](https://banes-lab.com/records/layer/correctness-core.md)
Canonical: https://banes-lab.com/ontology/lexicon#lexicon-evaluation-suite

Listed in [Lexicon terms](https://banes-lab.com/api/records/lexicon.md), after [Prompt Versioning](https://banes-lab.com/records/lexicon/prompt-versioning.md) and before [Centralized Model Configuration](https://banes-lab.com/records/lexicon/centralized-model-configuration.md).

## Category

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

## Refactors

- [Prompt Sprawl](https://banes-lab.com/records/architecture/prompt-sprawl.md)
- [Artificial Intelligence Architecture](https://banes-lab.com/records/architecture/artificial-intelligence-architecture.md)
- [Model Governance](https://banes-lab.com/records/architecture/model-governance.md)
- [Model Evaluation](https://banes-lab.com/records/architecture/model-evaluation.md)
- [Vector Search](https://banes-lab.com/records/architecture/vector-search.md)
- [Model Safety](https://banes-lab.com/records/architecture/model-safety.md)

## Linked from

- [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)