Official prompt engineering guides
Curated guides from the teams building the models. 21 guides across 6 providers.
The Complete Prompt Engineering Guide
Everything from Anthropic's prompt engineering docs in one progressive guide. Clear instructions, multishot examples, chain of thought, XML tags, roles, chaining, long context, extended thinking, and Claude 4 best practices.
Be Clear and Direct
How to write clear, specific, and direct prompts that get Claude to do exactly what you want.
Use Examples (Multishot Prompting)
How to use few-shot examples to dramatically improve Claude's accuracy, consistency, and output quality.
Let Claude Think (Chain of Thought)
Encourage step-by-step reasoning to dramatically improve Claude's accuracy on complex tasks.
Use XML Tags to Structure Prompts
Structure your prompts with XML tags for clarity, accuracy, and easy parsing of Claude's output.
Give Claude a Role (System Prompts)
Use system prompts and role prompting to turn Claude from a general assistant into a domain expert.
Chain Complex Prompts
Break complex tasks into smaller subtasks for better accuracy, clarity, and traceability.
Long Context Prompting Tips
Techniques for leveraging Claude's 200K token context window with large documents and data.
Extended Thinking Tips
Advanced strategies for getting the most out of Claude's extended thinking mode on complex problems.
Prompt Improver
Use Anthropic's automated prompt improver to optimize your prompts with chain-of-thought and XML structure.
Claude 4 Best Practices
Specific prompting strategies and best practices for Claude 4 models.
Context Engineering for Agents
How to design effective context for AI agents — memory, tool results, and orchestration.
The Complete OpenAI Prompt Engineering Guide
Everything from OpenAI's official prompt engineering docs. Six core strategies with tactics, examples, and real before/after comparisons.
GPT-4.1 Prompting Guide
Prompting techniques specific to GPT-4.1. Covers agentic workflows, 1M token context, literal instruction following, and the planning patterns that boosted SWE-bench by 4%.
Best Practices (Help Center)
OpenAI's concise, no-nonsense best practices. Quick wins for prompt formatting, temperature tuning, few-shot examples, and avoiding common mistakes.
The Complete Gemini Prompting Guide
Everything from Google's Gemini prompting docs. Four input types, few-shot patterns, multimodal handling, parameter tuning, and agentic workflow strategies.
Gemini 3 Prompting Guide
Gemini 3 specific quirks and techniques on Vertex AI. Temperature gotchas, thinking modes, persona grounding, verbosity control, and multi-source synthesis.
Workspace Prompt Guide
Prompting Gemini inside Docs, Sheets, Slides, and Gmail. Google's official framework: persona, task, context, and format. Practical patterns for everyday productivity.
Llama Docs & Prompt Guide
Everything you need for Meta's open-source Llama models. Chat templates, system prompts, local deployment with Ollama, fine-tuning with LoRA, and production serving.
Prompting Capabilities
Mistral's official prompting guide. System prompt design, JSON mode, function calling, worded rating scales, and the specific anti-patterns to avoid.
Azure OpenAI Prompt Engineering
Microsoft's enterprise-focused guide for Azure OpenAI. Five prompt components, recency bias exploitation, grounding with citations, and the 'double down' technique.