Prompt engineering
Definition
Prompt engineering is the practice of specifying, in writing, what a model must do: the task, the rules, the input format and the required output structure. In production systems prompts are versioned artefacts, tested against real cases like any other code.
Business-grade prompts encode the company's actual rules — approval thresholds, wording conventions, exception handling — so results are consistent across thousands of cases.
The measurable difference comes from structured output and evaluation: forcing a fixed schema and testing changes against a fixed set of past cases before rollout.
In practice
- Prompts are versioned, reviewed and regression-tested
- Structured output makes results machine-checkable
- Company rules belong in the prompt or the tools, not in the user's head
Related terms
- Large language model (LLM)A large language model is a statistical model trained on very large text corpora that predicts likely continuations of text. It can classify, summarise, translate and draft, and it is the reasoning component inside most AI agents — but it holds no live company data by itself.
- GuardrailsGuardrails are the technical limits around an AI system: allowed tools, value ranges, spending and volume caps, forbidden actions and mandatory approvals. They turn an unpredictable model into a system that fails safely and visibly.
- Fine-tuningFine-tuning further trains an existing model on company-specific examples so it adopts a style, format or classification behaviour. It changes how a model responds, not what current facts it knows, and is usually the last option after prompting and retrieval.