A Taxonomy of Single-Turn Textual Prompt Patterns
For researchers and practitioners in prompt engineering, this provides a structured classification to standardize terminology and facilitate pattern reuse.
The paper addresses the lack of a unified taxonomy for single-turn textual prompt patterns in LLM interactions, identifying 30 canonical patterns organized along two dimensions.
Large language models (LLMs) are now widely employed in software development and everyday use. Interacting with LLMs requires crafting prompts, which range from simple ad hoc sentences to extensive, detailed, and structured instructions. Knowledge about prompt engineering has been documented in several surveys and catalogs in the literature. However, the term ``prompt pattern'' is defined differently across sources, and existing works have classified prompt patterns in different ways. In this report, we present a taxonomy of prompt patterns for single-turn, text-based interactions. Following a reproducible method, we identified 30 unique and canonical prompt patterns, organized along two dimensions.