26 Principles of Good Prompts
The 26 principles of good prompts are a set of 26 practical rules for writing prompts to large language models, introduced in the December 2023 paper Principled Instructions Are All You Need for Questioning…
Prompt Engineering
Explore Prompt Engineering through related topics and the articles other pages reference most.
Most linked
The Prompt Engineering articles that other AI Wiki pages link to most.
- Chain-of-ThoughtChain-of-thought (CoT) is a sequence of intermediate steps that a language model generates before its final answer.
- System promptA system prompt is a special set of instructions, guidelines, persona definitions, and contextual information given to a large language…
- PromptA prompt is the input given to a generative AI model, particularly a large language model (LLM), that elicits a desired response.
- Tree of ThoughtsTree of Thoughts (ToT) is a prompting and inference-time search framework for large language models that lets the model explore multiple…
- ReAct (prompting)ReAct (short for Reasoning and Acting) is a prompting paradigm for large language models that interleaves verbal reasoning traces…
- Self-consistencySelf-consistency is a decoding strategy for large language models that samples multiple chain-of-thought reasoning paths for the same…
- Zero shot, one shot and few shot learningZero-shot, one-shot, and few-shot learning are three related settings in machine learning and prompt engineering defined by how many…
- Context engineeringContext engineering is the practice of designing, building, and optimizing the full set of information that a large language model receives…
Explore articles
Browse subtopics (15)
Articles that also belong to these categories. Counts cover all of Prompt Engineering.
All articles (27)Large Language Models (13)Natural Language Processing (5)Artificial Intelligence (4)Machine Learning (4)AI Agents (3)Reasoning Models (3)ChatGPT (2)AI Code Generation (1)AI Inference (1)AI Safety (1)AI Tools & Products (1)Deep Learning (1)Image Generation (1)OpenAI (1)Software Development (1)
Showing 1-27 of 27 articles
Agentic Context Engineering
Agentic Context Engineering (ACE) is a framework for scalable and efficient context adaptation in large language models (LLMs) that lets an AI system improve itself by treating its own context as an evolving
Auto-CoT
Auto-CoT (Automatic Chain of Thought) is an automated prompting method that builds few-shot Chain-of-Thought demonstrations for large language models without any human-written exemplars, introduced by…
Chain of Density prompting
Chain of Density (CoD) is a prompting technique for abstractive text summarization with large language models, introduced in the 2023 paper "From Sparse to Dense: GPT-4 Summarization with Chain of Density…
Chain of Verification (CoVe)
Chain of Verification (CoVe) is a prompting technique that reduces factual hallucinations in large language models by having the model fact-check its own draft response through a structured four-step…
Chain-of-Thought
Chain-of-thought (CoT) is a sequence of intermediate steps that a language model generates before its final answer.
Context engineering
Context engineering is the practice of designing, building, and optimizing the full set of information that a large language model receives in its context window at inference time
CustomGPT Instructions for Knowledge (Uploaded Files)
"CustomGPT Instructions for Knowledge (Uploaded Files)" is the informal name for a short block of default instructions that OpenAI prepends to a Custom GPT's system prompt whenever the builder attaches files…
Fine-tune ChatGPT with Perplexity, Burstiness, Professionalism, Randomness and Sentimentality Guide
The perplexity, burstiness, professionalism, randomness, and sentimentality guide is a prompt engineering pattern that asks ChatGPT to write according to five style sliders, each rated 1 to 10, so a user can…
Graph of Thoughts
Graph of Thoughts (GoT) is a prompting and reasoning framework that models the intermediate steps of a large language model as an arbitrary directed graph rather than a linear chain or a tree.
How to Pressure LLMs for Better Output
Pressuring large language models (LLMs) is a family of prompt engineering techniques that try to push a model toward better output by adding emotional weight, urgency, stakes, or coercion to the prompt.
Least-to-Most Prompting
Least-to-Most Prompting is a few-shot prompting technique for large language models introduced by researchers at Google Brain in May 2022.
Meta Prompting
Meta prompting (also spelled meta-prompting) is an advanced prompt engineering technique where large language models (LLMs) are used to generate, refine, critique, select, or optimize prompts for themselves or…
MidJourney Prompt Generator
MidJourney Prompt Generator is a generic category name that refers to the broad class of tools, custom GPTs, and prompt templates that help users compose effective text prompts for Midjourney
Prompt
A prompt is the input given to a generative AI model, particularly a large language model (LLM), that elicits a desired response.
Prompt engineering for image generation
Prompt engineering for image generation is the practice of writing and refining the text prompts that guide text-to-image AI image generation models such as Stable Diffusion, Midjourney, DALL-E, Flux, and Nano…
Prompt engineering for text generation
Prompt engineering for text generation is the practice of designing the natural-language input (the prompt) given to a large language model so that it produces the desired text output
ReAct (prompting)
ReAct (short for Reasoning and Acting) is a prompting paradigm for large language models that interleaves verbal reasoning traces ("Thoughts") with task-specific actions executed against an external…
Self-Discover prompting
Self-Discover is a prompting framework for large language models in which the model first composes a task-specific reasoning structure from a library of atomic reasoning modules
Self-Refine
Self-Refine is an inference-time prompting framework in which a single large language model iteratively improves its own output by alternating between generating natural-language feedback on a draft and…
Self-consistency
Self-consistency is a decoding strategy for large language models that samples multiple chain-of-thought reasoning paths for the same question and returns the answer that the majority of those paths agree on
Skeleton-of-Thought
Skeleton-of-Thought (SoT) is a prompting technique for large language models that reduces end-to-end generation latency by first eliciting a short outline of the answer (the "skeleton") and then expanding each…
Step-Back Prompting
Step-Back Prompting is a two-stage prompting technique introduced by researchers at Google DeepMind in October 2023.
System prompt
A system prompt is a special set of instructions, guidelines, persona definitions, and contextual information given to a large language model (LLM) before any user input
Tree of Thoughts
Tree of Thoughts (ToT) is a prompting and inference-time search framework for large language models that lets the model explore multiple intermediate reasoning steps as nodes in a tree, evaluate each…
Vibe Coding Tips and Tricks
Vibe coding is the practice of building software by describing what you want in natural language and letting an AI write the code.
Zero shot, one shot and few shot learning
Zero-shot, one-shot, and few-shot learning are three related settings in machine learning and prompt engineering defined by how many labelled examples a model sees of a target task or class before making a…