Prompt Engineering
is the process of designing, testing, and refining inputs to guide —such as , , and —toward accurate, relevant, and useful outputs. It uses techniques such as and , along with instructions supplied through , to improve performance across tasks without modifying the underlying . Effective practice includes providing clear constraints, selecting relevant context within a model’s , and leveraging . These approaches can help mitigate but do not guarantee factual accuracy or reliable instruction following. Prompt engineering also supports and , where prompts guide how models use retrieved information and interact with tools. Organizations including , , and incorporate such strategies into systems that apply in production environments.
[PREVIEW MODE] Definitions streamed at five depths, references, and related terms are available to signed-in readers — [SIGN IN]
Contextual terminology map
KEEP IN VIEW
Ethics, safety & society
Moving as fast as the field, and easier to overlook
- Explainable AI
- Interpretability
- Model Card
- AI Audit
- Algorithmic Bias
- Disparate Impact
- Digital Divide
- WCAG (Web Content Accessibility Guidelines)
- AI Alignment
- Red Teaming
- EU AI Act
- NIST AI RMF (AI Risk Management Framework)
- Frontier Model
- Deepfake
- Content Credentials
- AI Watermarking
- Job Displacement
- Prompt Injection
- Data Poisoning
- Differential Privacy
- GDPR (General Data Protection Regulation)
- Zero-Day
- End-to-End Encryption
- Data Broker
Infrastructure, markets & the economy
The compute, power and capital behind the boom