Last reviewed: June 6, 2026

What are prompting patterns? Definition and right instinct vs wrong instinct

Prompting patterns are formulation conventions that structure a prompt to orient the model's output. They do not exist as native LLM commands, only as guides for the writer. The distinction matters: no pattern triggers a feature, the effect comes from linguistic precision.

You may have come across graphics listing 80 or 90 "Claude commands". These commands do not exist technically: the Claude LLM has no native slash-commands system. They are prompting patterns, writing conventions that structure the request without triggering a specific feature on the model side. The distinction matters. A pattern is not an instruction interpreted by the model as a technical directive, it is a linguistic convention applied by the user to clarify intent. The real value of patterns is cognitive: they help the writer structure thinking before prompting (role, context, constraints, expected reasoning), and statistically, better-structured prompts produce better-targeted outputs. No magic on the model side, just writing discipline on the human side. The WYP grid retains 12 recurrent patterns selected for executive utility: assigned role, input context, output constraints, chain-of-thought, few-shot, refuse to invent, sources requested, adversarial critique, reformulation, structured comparison, listed assumptions, pre-mortem.

Concrete example

A French mid-cap consulting firm CEO (180 employees) compares in 2026 two prompting approaches on 20 successive requests to Claude (competitive briefings). First try: vague prompts like "give me a summary of market X". Average output rated useful 4/10 on the internal scoring grid. Second try: systematic application of 4 combined patterns (assigned role "senior analyst", one-page context, output constraints three columns plus 300 words, explicit chain-of-thought). Average output 7.5/10 on the same grid. Difference not linked to the model (identical), only to writing discipline. Prompt drafting time: 3 minutes instead of 30 seconds, i.e. 2 minutes 30 additional for a qualitative gain of 75%.

Good vs bad reflex

BAD REFLEX

Printing the 89 commands from the LinkedIn graphic, sticking them next to the keyboard, and believing you have turned your team into experts. First problem: these patterns are not commands, so nobody knows when to trigger them. Second problem: 89 patterns is unmanageable operationally, and half are redundant or marginal. Third problem: a pattern without the discipline of application produces nothing. A team that knows the 89 patterns without practising them 20 times remains exactly at the same level as a team that prompts by feel.

GOOD REFLEX

Adopt 5 to 8 recurring patterns, industrialise them in shared templates (internal snippets, team prompt library), and measure the quality gap before/after on a sample of real requests. Have each pattern practised at least 20 times by each user before enriching it. Prioritise patterns with cognitive value (role, context, constraints, chain-of-thought, refuse to invent) over decorative patterns. Document cases where each pattern is worthwhile and those where it adds nothing, to avoid over-prompting. Usage discipline matters more than the number of patterns known.

Sources

Prompt engineering overview, official Anthropic documentation, 2026. https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/overview (accessed 2026-06-06)
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models, Wei, Wang, Schuurmans, Bosma, Ichter, Xia, Chi, Le, Zhou, arXiv 2201.11903, 2022 (revised January 2023). https://arxiv.org/abs/2201.11903 (accessed 2026-06-06)
Language Models are Few-Shot Learners, Brown et al., arXiv 2005.14165, 2020 (reference GPT-3 paper introducing few-shot learning through prompting). https://arxiv.org/abs/2005.14165 (accessed 2026-06-06)

← Back to glossary

What are prompting patterns? Definition and right instinct vs wrong instinct

Concrete example

See also

Further reading

Sources