Prompt Engineering
Prompt engineering is the practice of designing effective prompts to elicit desired outputs from large language models (LLMs).
## Prompt Chaining: Building AI Workflows
Instead of asking an LLM to 'write a 3000-word research report' in one go (which often results in shallow content), expert prompters use Prompt Chaining.
1. Prompt 1: Generate a detailed outline.
2. Prompt 2: Write Section A based on the outline.
3. Prompt 3: Critique Prompt 2 for factual errors.
4. Prompt 4: Rewrite Section A using the critique.
This modular approach ensures the model remains within its 'context window' efficiency and maintains high quality across large tasks.
graph LR
Center["Prompt Engineering"]:::main
Pre_natural_language_processing["natural-language-processing"]:::pre --> Center
click Pre_natural_language_processing "/terms/natural-language-processing"
Rel_hallucination_ai["hallucination-ai"]:::related -.-> Center
click Rel_hallucination_ai "/terms/hallucination-ai"
Rel_chain_of_thought["chain-of-thought"]:::related -.-> Center
click Rel_chain_of_thought "/terms/chain-of-thought"
Rel_generative_ai_agents["generative-ai-agents"]:::related -.-> Center
click Rel_generative_ai_agents "/terms/generative-ai-agents"
classDef main fill:#7c3aed,stroke:#8b5cf6,stroke-width:2px,color:white,font-weight:bold,rx:5,ry:5;
classDef pre fill:#0f172a,stroke:#3b82f6,color:#94a3b8,rx:5,ry:5;
classDef child fill:#0f172a,stroke:#10b981,color:#94a3b8,rx:5,ry:5;
classDef related fill:#0f172a,stroke:#8b5cf6,stroke-dasharray: 5 5,color:#94a3b8,rx:5,ry:5;
linkStyle default stroke:#4b5563,stroke-width:2px;
🧒 Explain Like I'm 5
🪄 The art of giving clear, specific instructions to an AI so it does exactly what you need.
🤓 Expert Deep Dive
## Prompt Chaining: Building AI Workflows
Instead of asking an LLM to 'write a 3000-word research report' in one go (which often results in shallow content), expert prompters use Prompt Chaining.
1. Prompt 1: Generate a detailed outline.
2. Prompt 2: Write Section A based on the outline.
3. Prompt 3: Critique Prompt 2 for factual errors.
4. Prompt 4: Rewrite Section A using the critique.
This modular approach ensures the model remains within its 'context window' efficiency and maintains high quality across large tasks.