Prompting Glossary
Browse 18 prompting terms defined in plain English, from the cultural dictionary of computing.
18 Prompting Terms
- AI Prompt Engineer
- A person focused on designing, iterating, and evaluating prompts or AI workflows to get reliable behavior from models. In cultural conversations the term is...
- Anchor Token
- A token or phrase in a prompt that strongly steers model behavior because it anchors interpretation, format, or topic.
- Chain of Density
- A prompting approach for iterative summarization in which each revision preserves important information while becoming more information-dense and compact. It...
- Chain of Thought
- Chain of Thought is a prompting technique and reasoning approach in large language models where the model is encouraged to show its step-by-step reasoning...
- Chain of Thought Prompting
- A prompting technique that encourages a model to produce intermediate reasoning steps before the final answer. It influences how models are trained, evaluated,...
- Chain of Verification
- A prompting or workflow pattern where an AI system generates an answer and then explicitly checks or verifies important claims through additional reasoning or...
- Context Stuffing
- The practice of adding too much material to a prompt or context window in the hope that more information will improve the answer, often with diminishing...
- Few-Shot
- Describing a setup where a model is given a small number of examples in the prompt to demonstrate the desired behavior before handling a new input. Few-shot...
- Few-Shot Learning
- A technique where a model learns to perform a task from just a handful of examples, either provided in the prompt (in-context learning) or during a brief...
- In-Context Learning
- A model behavior where examples placed in the prompt shape predictions without updating model weights. It influences how models are trained, evaluated, or...
- Prompt Leaking
- The exposure of hidden system prompts, private instructions, or internal context through model output or prompt-injection attacks.
- Scaffold
- A structured workflow around a model, including prompts, tools, retries, memory, or routing logic, used to make a system more capable than a raw single call.
- Soft Prompt
- A learnable prompt representation, typically implemented as trainable embeddings, that influences model behavior without changing the full model weights. Soft...
- Step-by-Step
- Describing instructions or outputs that proceed one step at a time rather than jumping directly to the conclusion. Step-by-step prompting is often used to...
- system prompt
- System prompt is the initial set of instructions given to a large language model (LLM) that defines its behavior, personality, constraints, and capabilities...
- Think Step by Step
- A prompting instruction intended to encourage the model to reason in a more deliberate multi-step way rather than answering immediately. It is commonly used in...
- Unlocking
- The act of revealing or eliciting stronger model performance through better prompting, tooling, data, or workflow design rather than through a new underlying...
- Zero-Shot
- Describing a setting where a model performs a task without being given task-specific examples in the prompt, relying instead on prior training and general...
Related Topics
- Ai (10 terms in common)
- Reasoning (4 terms in common)
- Llm (3 terms in common)
- Generalization (2 terms in common)
- Technique (2 terms in common)
- Adaptation (1 terms in common)
- Retrieval (1 terms in common)
- Learning (1 terms in common)
- Verification (1 terms in common)
- Data Exposure (1 terms in common)
- Summarization (1 terms in common)
- Ai Culture (1 terms in common)
- Workflows (1 terms in common)
- Behavior (1 terms in common)
- Security (1 terms in common)
- Agents (1 terms in common)
- Tokenization (1 terms in common)
- Jobs (1 terms in common)
- Capabilities (1 terms in common)
- Ml (1 terms in common)