Glossary Updates12 new terms added to the glossaries · October 2, 2026, 22:44 CEST
AI TechDocKnowledge

Glossary · 3 · Working with models: prompts and context

Few-shot prompting

Also known as: Zero-shot prompting, In-context learning, One-shot prompting

Few-shot prompting is the technique of including a small number of input–output examples in a prompt so that the model infers the desired pattern, style or format from them; with no examples it is called zero-shot prompting.

  • Intermediate
  • Technical writers
  • Technical marketers
  • Developers

In one sentence

Few-shot prompting explained: show an AI model two or three examples and it follows the pattern — ideal for style, format and terminology.

Example

To generate glossary definitions, the prompt includes three approved definitions from the house style guide, then asks for a new one in the same pattern.

Why it matters on your learning path

  • Technical writers: Examples from your style guide are often more effective than long style rules.
  • Technical marketers: Show two or three approved posts to get on-brand variants.
  • Developers: Few-shot examples consume context; for large numbers of examples consider fine-tuning.

By knowledge.aitechdoc.world · Published September 26, 2026 · Last reviewed

Source: Brown et al., “Language Models are Few-Shot Learners,” NeurIPS 2020

Definitions follow the cited standards and specifications. Where a source is a copyrighted publication, such as an ISO, IEC or EN standard, the definition is a close paraphrase, not a verbatim quotation, so as not to infringe copyright. We recommend reading the original publication. The sections “How it applies” are editorial commentary by AI TechDoc Knowledge and are not part of any standard.

Seen a mistake? Send us a note!