# Prompt Engineering

Record: `arch:prompt-engineering`
Kind: technique
Layer: [Correctness Core](https://banes-lab.com/records/layer/correctness-core.md)
Severity: contextual/mandatory for model-backed systems
Scope: model-backed system, language-model system, application
Canonical: https://banes-lab.com/ontology#arch-prompt-engineering

## Repair

- Refactored by: Centralize and Version Prompts
- Detected by: scattered prompt string literals
- Violated by: prompts inlined and duplicated across call sites
- Measured by: duplicated prompt count
- Enforced by: model design review

## requires

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

## reinforces

- [Model Evaluation](https://banes-lab.com/records/arch/model-evaluation.md)
- [Reproducibility](https://banes-lab.com/records/arch/reproducibility.md)

## enables

- [Structured, Versioned Prompts](https://banes-lab.com/records/lex/structured-versioned-prompts.md)

## conflicts-with

- [Prompt Sprawl](https://banes-lab.com/records/arch/prompt-sprawl.md)

## tensions-with

- [Robustness](https://banes-lab.com/records/lex/robustness.md)

## tensions

- [Prompt Engineering Robustness](https://banes-lab.com/records/tension/prompt-engineering-robustness.md)