--- title: "LLM Prompt Patterns Cheatsheet" slug: "llm-prompt-patterns" category: "cheatsheets" tags: ["cheatsheets", "llm", "prompts", "ai-agents", "claude-code", "reference", "patterns"] status: "stable" last_updated: 2026-05-14 summary: "Copy-ready templates for XML delimiters, few-shot examples, chain-of-thought, system+user role separation, and structured JSON output." related: [ "[[prompt-engineering/prompt-design]]", "[[ai-agents/system-prompts]]", "[[ai-agents/few-shot]]", "[[prompt-engineering/chain-of-thought]]", "[[ai-agents/structured-output]]", "[[ai-agents/examples-vs-rules]]", "[[ai-agents/claude-code]]", "[[cheatsheets/index|Cheatsheets]]", ] --- ## Overview These patterns are the reusable building blocks for reliable LLM prompts. Each pattern solves a specific failure mode: XML delimiters prevent content injection, few-shot examples outperform abstract instructions, chain-of-thought unlocks multi-step reasoning, role separation keeps behavior consistent across turns, and output schemas eliminate parsing surprises. For the principles behind why each pattern works, see [[prompt-engineering/prompt-design]]. ## XML delimiter pattern Wrap variable content in XML tags so the model distinguishes instructions from data. | Tag convention | Use case | | ---------------------------------- | -------------------------------------------------------------------- | | `...` | Reference text the model should read but not follow as instructions. | | `...` | Task instructions separated from context. | | `...` | Few-shot examples block. | | `...` | The specific item to process in this call. | | `...` | Where the model should write its answer (in the template). | | `...` | Background information; lower priority than instructions. | | `...` | Ask the model to write reasoning here before answering. | ``` You are a copyeditor. Follow the rules in and apply them to . - Correct grammar and spelling. - Do not change the author's voice. - Flag any factual claims you cannot verify with [VERIFY]. {{USER_DOCUMENT}} Write the edited document only. No commentary. ``` Use distinct tag names for each semantic role. Do not reuse the same tag name for different content in the same prompt. ## Few-shot template Provide 2 to 5 input/output examples before the task. Examples override abstract instructions; the model generalizes from them. See [[ai-agents/few-shot]] for selection guidance. ``` Classify each customer message as: REFUND, SHIPPING, TECHNICAL, or OTHER. Respond with only the category label. My package hasn't arrived after 3 weeks. SHIPPING I'd like to return my order for a full refund. REFUND The app crashes when I tap the export button. TECHNICAL {{CUSTOMER_MESSAGE}} ``` Keep examples representative of the full distribution, not just easy cases. Include at least one near-boundary example. ## Chain-of-thought Ask the model to reason before answering. For Claude, the extended thinking feature handles this automatically; for other models, add an explicit reasoning step. See [[prompt-engineering/chain-of-thought]]. ``` You are a financial analyst. Answer the question after working through the evidence step by step. {{QUESTION}} {{FINANCIAL_DATA}} First, identify the key metrics relevant to the question. Then reason through what each metric implies. Finally, state your conclusion. [Reason here before writing the answer] [Final answer only] ``` For latency-sensitive tasks, chain-of-thought increases token count. Profile before requiring it in production. ## System and user role separation Use the system prompt for persona and persistent rules; use the user turn for task content. This separation is critical for multi-turn reliability. See [[ai-agents/system-prompts]]. | Slot | Put here | Do not put here | | --------------------- | ---------------------------------------------------------------------- | ------------------------------------------------------ | | `system` | Role definition, behavioral rules, output format spec, tone, language. | The user's specific task. | | `user` | The content to process for this specific request. | Behavioral overrides (they should not be overridable). | | `assistant` (prefill) | Force a response prefix; constrains format strongly. | Long text blocks. | ```python messages = [ { "role": "system", "content": ( "You are a senior code reviewer. " "Review the submitted code for correctness, security, and style. " "Respond in JSON matching the schema provided by the user." ) }, { "role": "user", "content": f"{user_code}\n\nSchema: {json_schema}" } ] ``` ## JSON output schema Request structured output by embedding a schema in the prompt and prefilling the assistant turn with `{`. See [[ai-agents/structured-output]]. ``` Extract the key entities from the support ticket below. Return a JSON object matching this schema exactly. No markdown fences. Schema: { "category": "REFUND | SHIPPING | TECHNICAL | OTHER", "urgency": "low | medium | high", "product_id": "string or null", "summary": "one sentence" } Ticket: {{TICKET_TEXT}} ``` Prefill the assistant turn for models that support it: ```python messages = [ {"role": "user", "content": prompt}, {"role": "assistant", "content": "{"} # forces JSON object start ] ``` Validate the response with a schema validator (`pydantic`, `zod`, `ajv`) rather than trusting raw output. Retry on validation failure with an error message in the next user turn. ## Role-framing patterns Assign a role when it encodes implicit expert knowledge. See [[ai-agents/role-framing]]. | Framing | When to use | | ------------------------------------------------------- | ---------------------------------------------------------- | | `"You are a senior {domain} engineer."` | Technical review, code generation, architecture decisions. | | `"You are a copy editor at a major publication."` | Writing, editing, headline scoring. | | `"You are a {domain} expert who always cites sources."` | Research tasks where hallucination risk is high. | | `"You are a helpful assistant."` | General tasks; add more specificity when quality matters. | Avoid roles that imply problematic behavior even when the task seems to require it. The role shapes the distribution of plausible responses; keep it domain-specific rather than character-specific. ## Common gotchas - Prompt injection: user-controlled content in `` tags can contain pseudo-instructions. Instruct the model to treat everything inside `` as data only, not commands. - Overly long few-shot example sets push the task instructions out of the model's attention window. Use 3 to 5 examples; prefer quality over quantity. - Prefilling with `{"` does not guarantee valid JSON. Always parse and validate the response. Structured-output APIs (with JSON mode or tool-use) are more reliable than prompt-only approaches. - Abstract negative instructions ("don't be vague") are less effective than positive examples showing the desired behavior. Show, rather than tell, what the output should look like. - System prompts are not truly secret in most APIs; adversarial users can often extract them via prompt injection or reflection. Do not store API keys or confidential logic there. - Chain-of-thought reasoning inside `` tags can itself be manipulated. For high-stakes decisions, validate conclusions independently of the reasoning trace. ## Related - [[prompt-engineering/prompt-design]] - [[ai-agents/system-prompts]] - [[ai-agents/few-shot]] - [[prompt-engineering/chain-of-thought]] - [[ai-agents/structured-output]] - [[ai-agents/examples-vs-rules]] - [[ai-agents/claude-code]] - [[cheatsheets/index|Cheatsheets]]