Prompt Engineering

Related Terms

• Evaluation Set (Evals)

  An evaluation set is a fixed collection of inputs with expected outcomes, used to score an AI system the same way every time it changes. It plays the role a regression test suite plays for ordinary code.

• Context Window

  A context window is the maximum amount of text, counted in tokens, that a language model can take into account in one request. It covers the instructions, the conversation, any retrieved documents and the reply.

• Prompt Engineer

  A prompt engineer designs, tests and refines the instructions and context given to AI models so they produce accurate, consistent and safe output. For buyers, the key question is whether that work needs a dedicated role or sits within AI engineering.

• RAG vs Fine-Tuning

  RAG gives a language model relevant documents at the moment it answers, while fine-tuning retrains the model's weights on custom examples. RAG suits changing facts that need citing; fine-tuning suits fixed styles, formats or specialised skills.