Prompt Engineering Guide — Topics Covered
Fundamentals
- Zero-shot prompting — No examples, just instructions
- Few-shot prompting — Learning from examples
- Chain-of-thought (CoT) — Step-by-step reasoning
- Self-consistency — Multiple reasoning paths
- Tree-of-thoughts — Branching exploration
Advanced Techniques
- Retrieval Augmented Generation (RAG) — Ground responses in external data
- ReAct prompting — Reasoning + acting for agents
- Function calling — LLM triggers external tools
- Multimodal prompting — Text + images + audio
AI Agents
- Agent architectures and patterns
- Tool use and orchestration
- Memory and planning
- Multi-agent systems
Safety & Security
- Adversarial prompting attacks
- Prompt injection defense
- Jailbreak prevention
- Output validation
Model-Specific Guides
GPT-4, ChatGPT, Claude, Gemini, Llama 3, Mistral, Phi, Cohere, and more.
FAQ
Q: What is the Prompt Engineering Guide? A: The most comprehensive open-source learning resource for prompt engineering, covering fundamentals to advanced techniques across all major LLMs. 72,900+ stars, 3M+ learners.
Q: Is it free? A: Yes, MIT license. Additional paid courses available through DAIR.AI Academy.