Prompt Patterns

The dozen prompting techniques that actually move quality, with the one-line version of when to use each.

Structure

Role + task + constraints: who the model is, what to produce, what must never happen — in that order
Few-shot examples: 2-5 input→output pairs beat a paragraph of description; match format exactly
Output schema: ask for JSON against a schema (or use structured output mode) — parse, don’t regex
Delimiters: fence retrieved/user content (<doc>…</doc>) and say it is data, not instructions
Prefill the start: begin the assistant turn ("{") to lock format and skip preamble

Chain-of-thought: "think step by step" / worked examples — for math, logic, multi-step
Self-consistency: sample N answers, majority-vote — reliability on discrete answers
Decompose: split into subtasks across calls; each prompt does ONE job well
Critique-then-revise: second pass: "find errors in this answer, then fix them"
Reasoning models: o1/R1-class: skip CoT prompting — state the problem, set effort, stay out of the way

Grounding: "answer ONLY from the sources; cite; say not-found otherwise" — kills most hallucination
Escape hatch: always give an out ("if unsure, say so") — forced answers are invented answers
Position matters: models recall start + end best — instructions up top, key facts near the question
Temperature: 0-0.3 for tools/extraction · 0.7+ for ideation; seeds for reproducibility
Cache-aware order: stable content (system, tools, examples) first; volatile (query) last