# SurePrompts > SurePrompts is an AI-powered prompt generator and template library that turns plain-English descriptions into expert-level prompts for ChatGPT, Claude, Gemini, and other major LLMs. SurePrompts pairs an AI generator with 350+ guided templates so users can build structured prompts in under 60 seconds — no account required. The site also publishes original prompt-engineering research, model-specific guides, and a 200+ term glossary covering modern LLM concepts. All content is written for practitioners who need techniques that actually work on 2026-era frontier models. ## Named Frameworks - [SurePrompts Quality Rubric](https://sureprompts.com/blog/sureprompts-quality-rubric): A 7-dimension scoring framework (Role clarity, Context sufficiency, Instruction specificity, Format structure, Example quality, Constraint tightness, Output validation) for evaluating prompt quality. Max score 35. - [RCAF Prompt Structure](https://sureprompts.com/blog/rcaf-prompt-structure): A 4-part prompt skeleton — Role, Context, Action, Format — for writing maintainable prompts that survive model upgrades. - [Context Engineering Maturity Model](https://sureprompts.com/blog/context-engineering-maturity-model): A 5-level progression from static hand-written prompts (L1) to multi-source orchestration with semantic caching and evaluation loops (L5). Self-assessment tool for teams. - [Agentic Prompt Stack](https://sureprompts.com/blog/agentic-prompt-stack): A 6-layer model for designing agent prompts — Goals, Tool permissions, Planning scaffold, Memory access, Output validation, Error recovery. ## Pillar Guides - [Every Prompt Engineering Technique Explained: The Research-Backed Guide (2026)](https://sureprompts.com/blog/advanced-prompt-engineering-techniques): Master 12 prompt engineering techniques with research data, benchmarks, and copy-paste templates. - [AI Image Prompting: The Complete 2026 Guide](https://sureprompts.com/blog/ai-image-prompting-complete-guide-2026): The canonical 2026 guide to AI image prompting — a universal six-slot anatomy, the model landscape (Midjourney V7, DALL-E, Flux Pro, Stable Diffusion, Imagen... - [Multimodal AI Prompting: The Complete 2026 Input Guide](https://sureprompts.com/blog/ai-multimodal-prompting-complete-guide-2026): The canonical 2026 guide to multimodal INPUT prompting — sending images, PDFs, screenshots, audio, and video into text models for analysis, extraction, and reasoning. - [Prompting Reasoning Models in 2026: GPT-5.5, Claude, Gemini, and DeepSeek](https://sureprompts.com/blog/ai-reasoning-models-prompting-complete-guide-2026): How to prompt GPT-5.5 reasoning effort, Claude adaptive thinking, Gemini 3.1 Pro thinking, and DeepSeek V4 in 2026 — the 6-slot anatomy, per-model dialects, and when to skip them. - [AI Video Prompting: The Complete 2026 Guide](https://sureprompts.com/blog/ai-video-prompting-complete-guide-2026): The canonical 2026 guide to AI video prompting — extended anatomy for motion, camera, duration, and audio, the model landscape (Veo 3, Sora 2, Runway Gen-3, ... - [AI Voice and Audio Prompting: The Complete 2026 Guide](https://sureprompts.com/blog/ai-voice-audio-prompting-complete-guide-2026): The canonical 2026 guide to voice and audio prompting for OUTPUT — TTS, voice cloning, realtime conversational voice, and voice agents. - [Best AI Model in 2026: ChatGPT vs Claude vs Gemini Compared](https://sureprompts.com/blog/complete-guide-ai-models-2026): Which AI model wins for coding, writing, and research in 2026? - [The Complete Guide to AI Prompt Engineering: From Beginner to Expert](https://sureprompts.com/blog/complete-guide-ai-prompt-engineering): Master the art and science of crafting prompts that unlock AI's full potential—from basic techniques to advanced strategies used by Fortune 500 companies - [Context Engineering: The 2026 Replacement for Prompt Engineering](https://sureprompts.com/blog/context-engineering-the-2026-replacement-for-prompt-engineering): How context engineering — the discipline of assembling what a model sees — replaced prompt engineering as the 2026 quality lever. - [Enterprise AI Adoption: The Complete 2026 Operating Model Guide](https://sureprompts.com/blog/enterprise-ai-adoption-2026-operating-model-guide): The canonical 2026 guide to adopting AI as an operating model — use-case taxonomy, governance, build-vs-buy, budgets, fluency, security and compliance, vendo... - [Prompt Engineering for Business Teams: Marketing, Sales, Engineering, Ops](https://sureprompts.com/blog/prompt-engineering-for-business-teams-2026): How business teams prompt AI for real work — briefs, discovery, architecture reviews, SOPs. - [The Complete Guide to Prompting AI Coding Agents (2026)](https://sureprompts.com/blog/the-complete-guide-to-prompting-ai-coding-agents-2026): How to prompt 2026's AI coding agents — Claude Code, Cursor, Devin, Replit Agent, and more. ## Canonical references - [The Agentic Prompt Stack: 6 Layers for Designing Prompts That Run Agents](https://sureprompts.com/blog/agentic-prompt-stack): The Agentic Prompt Stack organizes agent prompts into 6 layers — Goals, Tool permissions, Planning scaffold, Memory access, Output validation, Error recovery... - [The Context Engineering Maturity Model: 5 Levels From Static Prompts to Orchestrated Systems](https://sureprompts.com/blog/context-engineering-maturity-model): A 5-level maturity model for context engineering, from static hand-written prompts (L1) to multi-source orchestration with semantic caching and evaluation loops (L5). - [Fine-tuning vs Prompting vs RAG: The Complete 2026 Decision Guide](https://sureprompts.com/blog/fine-tuning-vs-prompting-vs-rag-2026): Three distinct levers for adapting a frontier LLM to your work — prompting, retrieval-augmented generation, and fine-tuning — with very different cost shapes... - [LLM Temperature and Sampling: The Complete 2026 Reference Guide](https://sureprompts.com/blog/llm-temperature-sampling-complete-guide-2026): A developer reference for the sampling parameters that shape every LLM output — temperature, top-p, top-k, frequency and presence penalties, seed, stop sequences, and max tokens. - [Model Context Protocol (MCP): The Complete 2026 Guide](https://sureprompts.com/blog/model-context-protocol-mcp-complete-guide-2026): MCP is the open standard from Anthropic that lets any compliant LLM client talk to any compliant tool, resource, or prompt server — collapsing the n×m integration problem into n+m. - [Prompt Evaluation: The Complete 2026 Guide to Measuring Prompt Quality](https://sureprompts.com/blog/prompt-evaluation-complete-guide-2026): How to actually evaluate prompts in production — the evaluation pyramid, golden sets, LLM-as-judge automation, regression suites, and the observability layer that catches drift before users do. - [Prompt Injection Defense: The Complete 2026 Security Guide](https://sureprompts.com/blog/prompt-injection-defense-complete-guide-2026): Prompt injection is the SQL injection of the LLM era — direct, indirect, and jailbreak variants — and the defenses in 2026 are imperfect but real, layered, and worth building. - [The RCAF Prompt Structure: A 4-Part Skeleton for Maintainable Prompts](https://sureprompts.com/blog/rcaf-prompt-structure): RCAF is a 4-part prompt skeleton — Role, Context, Action, Format — that produces maintainable prompts by separating identity, background, task, and output shape. - [The SurePrompts Quality Rubric: A 7-Dimension Framework for Scoring Prompts](https://sureprompts.com/blog/sureprompts-quality-rubric): A structured way to evaluate prompt quality across 7 dimensions, scored 1-5 each for a max of 35. ## Prompt Generator Tools - [AI Prompt Generator](https://sureprompts.com/ai-prompt-generator): Turn simple requests into detailed, expert-level AI prompts in seconds. Refine with follow-up instructions. Optimized for ChatGPT, Claude, Gemini, Grok, Llama and more. - [Prompt Generator](https://sureprompts.com/prompt-generator): Generate optimized AI prompts with our free prompt generator. Works with ChatGPT, Claude, Gemini, and all major AI models. No signup required. - [ChatGPT Prompt Generator](https://sureprompts.com/chatgpt-prompt-generator): Free ChatGPT prompt generator. Create optimized prompts for GPT-5.5 and ChatGPT with 350+ templates. Guided builder with real-time preview. - [Claude Prompt Generator](https://sureprompts.com/claude-prompt-generator): Free Claude prompt generator. Create optimized prompts for Claude Opus 4.8, Sonnet 4.6, and Haiku 4.5 with 350+ templates. Guided builder with real-time preview. - [Gemini Prompt Generator](https://sureprompts.com/gemini-prompt-generator): Free Gemini prompt generator. Create optimized prompts for Gemini 3.1 Pro and Gemini 2.5 Flash with 350+ templates. Guided builder with real-time preview. ## Template Categories - [AI & Automation](https://sureprompts.com/templates/ai): Generate AI prompts, model configurations, and AI-related content. - [Business](https://sureprompts.com/templates/business): Enhance business operations with AI-generated business plans, proposals, and strategic documents. - [Content](https://sureprompts.com/templates/content): Generate engaging content including articles, outlines, and creative writing pieces. - [Data & Analytics](https://sureprompts.com/templates/data): Analyze data and create comprehensive reports with AI-powered data analysis templates. - [HR & People](https://sureprompts.com/templates/hr): Create HR documents, job descriptions, performance reviews, and employee communications. - [Legal](https://sureprompts.com/templates/legal): Draft legal documents, contracts, and compliance materials with AI assistance. - [Marketing](https://sureprompts.com/templates/marketing): Create professional marketing content with AI. Generate blog posts, social media content, email campaigns, and more. - [Operations](https://sureprompts.com/templates/operations): Streamline operations with AI-generated documentation, SOPs, reports, and process guides. - [Research](https://sureprompts.com/templates/research): Conduct thorough research and analysis with AI-powered research templates and summaries. - [Technical](https://sureprompts.com/templates/technical): Create technical documentation, code explanations, and developer-focused content with AI. - [Video & Media](https://sureprompts.com/templates/video): Create video scripts, storyboards, and video production prompts for AI video generation. - [All Templates](https://sureprompts.com/templates): Full catalog of 350+ free and Pro prompt templates across every category. ## Glossary Full glossary: [https://sureprompts.com/glossary](https://sureprompts.com/glossary) ### A - [Active Prompting](https://sureprompts.com/glossary/active-prompting): Active prompting is an adaptive approach to few-shot example selection that borrows from active learning. - [Agent Graph](https://sureprompts.com/glossary/agent-graph): An agent graph is a representation of an agentic LLM application as a directed graph of nodes (work units, often LLM calls or tools) connected by edges (transitions, often conditional on state). - [Agent Handoff](https://sureprompts.com/glossary/agent-handoff): An agent handoff is a pattern in multi-agent systems where one agent transfers control of the conversation or task to another agent — passing along context but ceding ownership of the loop. - [Agent Orchestration](https://sureprompts.com/glossary/agent-orchestration): Agent orchestration is the practice of designing how agents, tools, and state interact across a multi-step task. - [Agent Tool Loop](https://sureprompts.com/glossary/agent-tool-loop): An agent tool loop is the canonical agentic execution pattern: the model receives a goal, optionally calls a tool, observes the result, and decides whether to call another tool or finish. - [Agentic AI](https://sureprompts.com/glossary/agentic-ai): Agentic AI refers to AI systems that can autonomously plan, execute, and iterate on multi-step tasks with minimal human intervention. - [Agentic Coding](https://sureprompts.com/glossary/agentic-coding): Agentic coding is the umbrella term for autonomous, multi-step coding workflows in which an LLM-driven agent plans, executes (file edits, shell commands, tes... - [Agentic Prompt Stack](https://sureprompts.com/glossary/agentic-prompt-stack): The Agentic Prompt Stack is a 6-layer model for designing prompts that run AI agents: Goals, Tool permissions, Planning scaffold, Memory access, Output validation, and Error recovery. - [Agentic RAG](https://sureprompts.com/glossary/agentic-rag): Agentic RAG is a pattern where retrieval is treated as a tool call inside an agent loop rather than as a fixed first step in a linear pipeline. - [AI Agent](https://sureprompts.com/glossary/ai-agent): An AI agent is a software system that uses a large language model as its reasoning core to autonomously plan, execute, and adapt multi-step workflows using external tools and data sources. - [AI Alignment](https://sureprompts.com/glossary/ai-alignment): AI alignment is the field of research and practice focused on ensuring that AI systems behave in accordance with human values, intentions, and goals. - [AI Guardrails](https://sureprompts.com/glossary/ai-guardrails): AI guardrails are safety mechanisms, rules, and constraints built into AI systems to prevent harmful, biased, or undesired outputs. - [AI Hallucination Detection](https://sureprompts.com/glossary/ai-hallucination-detection): AI hallucination detection encompasses the methods, tools, and techniques used to identify when an AI model generates false, fabricated, or unsupported information. - [AI IDE](https://sureprompts.com/glossary/ai-ide): An AI IDE is a development environment in which an AI agent is the primary or co-equal interface for writing and editing code, rather than an autocomplete si... - [AI Overview](https://sureprompts.com/glossary/ai-overview): An AI Overview is an AI-generated summary box that appears at the top of Google search results, synthesizing information from multiple web sources to answer a user's query directly. - [AI Safety](https://sureprompts.com/glossary/ai-safety): AI safety is the interdisciplinary field focused on ensuring that AI systems behave as intended, remain under human control, and do not cause unintended harm. - [AI Watermarking](https://sureprompts.com/glossary/ai-watermarking): AI watermarking is the practice of embedding hidden, machine-detectable patterns into AI-generated content — text, images, audio, or video — so that the content can later be identified as AI-produced. - [Aider Polyglot](https://sureprompts.com/glossary/aider-polyglot): Aider Polyglot is a multi-language coding benchmark, originated by the Aider open-source project, that evaluates an AI agent's ability to satisfy hidden test... - [Answer Engine Optimization (AEO)](https://sureprompts.com/glossary/answer-engine-optimization): Answer engine optimization (AEO) is a content strategy focused on structuring web content to appear as direct answers in featured snippets, People Also Ask b... - [Attention Mechanism](https://sureprompts.com/glossary/attention-mechanism): An attention mechanism is a neural network component that allows a model to dynamically weigh the importance of different parts of the input when generating each part of the output. - [Auto-CoT (Automatic Chain of Thought)](https://sureprompts.com/glossary/auto-cot): Auto-CoT is a method for generating chain-of-thought demonstrations automatically rather than hand-writing them. - [Autonomous Agent](https://sureprompts.com/glossary/autonomous-agent): An autonomous agent is an AI system that can independently plan, decide, and execute multi-step tasks to achieve a goal with minimal human oversight. ### B - [Beam Search](https://sureprompts.com/glossary/beam-search): Beam search is a decoding strategy that explores multiple candidate output sequences simultaneously during text generation, keeping the top-k most probable sequences (the "beam width") at each step. - [Benchmark](https://sureprompts.com/glossary/benchmark): A benchmark in AI is a standardized test suite with predefined tasks, datasets, and evaluation metrics used to measure and compare model performance. - [Benchmark Contamination](https://sureprompts.com/glossary/benchmark-contamination): Benchmark contamination occurs when an AI model's training data accidentally or deliberately includes questions and answers from the benchmark tests used to evaluate it. - [Bi-Encoder](https://sureprompts.com/glossary/bi-encoder): A bi-encoder is a dual-tower transformer architecture in which the query and the document are encoded independently by the same (or twin) encoder into separa... - [BM25](https://sureprompts.com/glossary/bm25): BM25 is the dominant sparse-retrieval algorithm and the default scoring function in Elasticsearch, Lucene, OpenSearch, and most Postgres full-text setups. ### C - [Catastrophic Forgetting](https://sureprompts.com/glossary/catastrophic-forgetting): Catastrophic forgetting is a phenomenon where a neural network rapidly loses previously learned knowledge when it is trained on new data or tasks. - [Chain of Code](https://sureprompts.com/glossary/chain-of-code): Chain of Code is a hybrid reasoning pattern in which the model produces a trace that interleaves executable code with natural-language "pseudocode" comments. - [Chain of Density](https://sureprompts.com/glossary/chain-of-density): Chain of density is a summarization technique in which the model iteratively rewrites a summary, each pass adding more salient entities while keeping total length constant. - [Chain of Thought Prompting](https://sureprompts.com/glossary/chain-of-thought): Chain of thought prompting is a technique that encourages an AI model to break down complex reasoning into sequential, intermediate steps before arriving at a final answer. - [Chain of Verification](https://sureprompts.com/glossary/chain-of-verification): Chain of verification (CoVe) is a prompting technique where the AI model first generates an initial response, then creates specific verification questions ab... - [Chunking](https://sureprompts.com/glossary/chunking): Chunking is the process of splitting source documents into smaller pieces before they are embedded and indexed for retrieval. - [Cline](https://sureprompts.com/glossary/cline): Cline is an open-source autonomous coding agent that runs as a Visual Studio Code extension; the project was originally released as Claude Dev before adopting its current name. - [Code Interpreter](https://sureprompts.com/glossary/code-interpreter): A code interpreter is an AI capability that allows a model to write and execute code — typically Python — in a sandboxed environment to solve analytical, mathematical, or data processing tasks. - [CodeAct](https://sureprompts.com/glossary/codeact): CodeAct is a pattern, formalized in a 2024 paper by Wang et al. - [Coding Agent](https://sureprompts.com/glossary/coding-agent): A coding agent is an LLM system specialized for software-engineering tasks — reading code, editing files, running tests, executing shell commands, and iterating on results until a task is complete. - [ColBERT (Late Interaction Retrieval)](https://sureprompts.com/glossary/colbert): ColBERT is a retrieval architecture that sits between bi-encoders and cross-encoders. - [Computer Use](https://sureprompts.com/glossary/computer-use): Computer use is an Anthropic capability in which Claude controls a virtual computer via screenshots and keyboard/mouse actions. - [Constitutional AI](https://sureprompts.com/glossary/constitutional-ai): Constitutional AI (CAI) is a training methodology developed by Anthropic where an AI model is guided by a set of written principles (a "constitution") to sel... - [Context Caching](https://sureprompts.com/glossary/context-caching): Context caching is an optimization technique where AI providers store and reuse previously processed prompt prefixes across multiple API calls. - [Context Engineering](https://sureprompts.com/glossary/context-engineering): Context engineering is the discipline of deliberately assembling everything an AI model sees at inference time — system prompt, retrieved documents, conversa... - [Context Engineering Maturity Model](https://sureprompts.com/glossary/context-engineering-maturity-model): The Context Engineering Maturity Model is a 5-level framework for describing how sophisticated a team's context assembly practice is. - [Context Rot](https://sureprompts.com/glossary/context-rot): Context rot is the degradation of model performance as a context window fills up with more content. - [Context Stuffing](https://sureprompts.com/glossary/context-stuffing): Context stuffing is the technique of loading relevant information — documents, data, or examples — directly into an AI model's prompt to give it the knowledge needed to answer accurately. - [Context Window](https://sureprompts.com/glossary/context-window): A context window is the maximum amount of text (measured in tokens) that an AI model can process in a single interaction, including both the input prompt and the generated output. - [Contextual Compression](https://sureprompts.com/glossary/contextual-compression): Contextual compression is a preprocessing step that sits between retrieval and generation in a RAG pipeline. - [Contextual Retrieval](https://sureprompts.com/glossary/contextual-retrieval): Contextual Retrieval is a technique introduced by Anthropic in 2024 that prepends a short chunk-specific context summary to each chunk before it is embedded and indexed for BM25. - [Conversation Memory](https://sureprompts.com/glossary/conversation-memory): Conversation memory is memory scoped to a single conversation or session — the running context of the current dialogue. - [Corrective RAG (CRAG)](https://sureprompts.com/glossary/corrective-rag): Corrective RAG is a 2024 retrieval pattern that adds a relevance-grading step between retrieval and generation: every retrieved document is scored by a light... - [Cost Per Task](https://sureprompts.com/glossary/cost-per-task): Cost per task is the total cost — including input tokens, output tokens, tool-call overhead, and retry rate — to complete one unit of useful work with a language model. - [CrewAI](https://sureprompts.com/glossary/crewai): CrewAI is an open-source Python framework for building multi-agent systems based on the role/goal/backstory metaphor. - [Cross-Encoder](https://sureprompts.com/glossary/cross-encoder): A cross-encoder is a transformer architecture that takes a query and a candidate document as a single joint input — typically concatenated with a separator t... ### D - [Data Poisoning](https://sureprompts.com/glossary/data-poisoning): Data poisoning is an adversarial attack that corrupts an AI model's training data to manipulate its behavior in targeted ways. - [Deep Research](https://sureprompts.com/glossary/deep-research): Deep research is an AI capability where the model autonomously conducts multi-step web research to produce comprehensive, sourced reports on complex topics. - [Direct Preference Optimization (DPO)](https://sureprompts.com/glossary/direct-preference-optimization): Direct preference optimization (DPO) is a training technique that aligns AI models with human preferences by learning directly from pairs of preferred and re... - [Document AI (Layout-Aware Parsing)](https://sureprompts.com/glossary/document-ai): Document AI refers to techniques and services for extracting structured content from complex documents — layout, reading order, tables, figures, forms, handw... - [DSPy](https://sureprompts.com/glossary/dspy): DSPy is a programming framework, originally from Stanford, that treats prompts as functions with typed signatures rather than strings. ### E - [Embedding](https://sureprompts.com/glossary/embedding): An embedding is a numerical vector representation of text that captures its semantic meaning in a high-dimensional space. - [Embedding Model](https://sureprompts.com/glossary/embedding-model): An embedding model is a machine-learning model that maps text (or images, audio, code) to a fixed-dimensional vector such that semantically similar inputs land near each other in vector space. - [Emergent Behavior](https://sureprompts.com/glossary/emergent-behavior): Emergent behavior in AI refers to capabilities that appear unexpectedly in large language models as they scale up in size, without being explicitly programmed or trained for those tasks. - [Episodic Memory](https://sureprompts.com/glossary/episodic-memory): Episodic memory is memory of specific events tied to time and context — "what happened when, where, and with whom." The term comes from cognitive science (Tu... - [Eval Harness](https://sureprompts.com/glossary/eval-harness): An eval harness is infrastructure that runs a prompt or model against a fixed test set and computes aggregate scores per metric. - [Extended Thinking](https://sureprompts.com/glossary/extended-thinking): Extended thinking is a Claude feature that lets the model allocate additional reasoning tokens before producing its final answer, with a user-controllable thinking budget set per request. ### F - [Few-Shot Chain of Thought](https://sureprompts.com/glossary/few-shot-chain-of-thought): Few-shot chain of thought is a prompting technique that combines few-shot examples with explicit step-by-step reasoning demonstrations. - [Few-Shot Learning](https://sureprompts.com/glossary/few-shot-learning): Few-shot learning is a machine learning approach where a model learns to perform a new task from only a handful of training examples — sometimes as few as one to five. - [Few-Shot Prompting](https://sureprompts.com/glossary/few-shot-prompting): Few-shot prompting is a technique where you provide the AI model with a small number of examples (typically 2-5) within the prompt to demonstrate the desired format, style, or reasoning pattern. - [Fine-Tuning](https://sureprompts.com/glossary/fine-tuning): Fine-tuning is the process of further training a pre-trained AI model on a specific dataset to specialize its behavior for particular tasks or domains. - [Function Calling](https://sureprompts.com/glossary/function-calling): Function calling is an AI model capability where the model analyzes a user's prompt and generates structured JSON specifying which external function to invoke and what arguments to pass. - [Function-Calling Accuracy](https://sureprompts.com/glossary/function-calling-accuracy): Function-calling accuracy is how often a model correctly picks the right tool, passes valid arguments, and respects schema constraints when given a function-calling interface. ### G - [Generative Engine Optimization (GEO)](https://sureprompts.com/glossary/generative-engine-optimization): Generative engine optimization (GEO) is the practice of structuring and enhancing content so that AI-powered platforms — like ChatGPT, Perplexity, and Google... - [Golden Set](https://sureprompts.com/glossary/golden-set): A golden set is a curated collection of input-output pairs that represent the correct behavior for a given task. - [GraphRAG](https://sureprompts.com/glossary/graphrag): GraphRAG is a retrieval-augmented-generation variant that builds a knowledge graph from the source corpus — extracting entities, relationships, and community... - [Grok](https://sureprompts.com/glossary/grok): Grok is the family of conversational AI models built by xAI, distinguished from other major assistants by its real-time access to posts on X (formerly Twitter) and a less filtered response style. - [Grounding](https://sureprompts.com/glossary/grounding): Grounding is the practice of anchoring AI responses to specific, verifiable sources of information such as documents, databases, or real-time data. ### H - [Hallucination](https://sureprompts.com/glossary/hallucination): A hallucination occurs when an AI model generates information that sounds plausible but is factually incorrect, fabricated, or unsupported by its training data. - [Hybrid Search](https://sureprompts.com/glossary/hybrid-search): Hybrid search is a retrieval technique that combines keyword-based search — typically BM25 over an inverted index — with vector-based semantic search, and fu... - [HyDE (Hypothetical Document Embeddings)](https://sureprompts.com/glossary/hyde): HyDE is a retrieval technique in which the language model first generates a hypothetical answer to the user's query, and then that hypothetical answer — not ... ### I - [In-Context Learning](https://sureprompts.com/glossary/in-context-learning): In-context learning is the ability of a large language model to learn and adapt its behavior based on examples or instructions provided directly within the p... - [Indirect Prompt Injection](https://sureprompts.com/glossary/indirect-prompt-injection): Indirect prompt injection is a security vulnerability in which malicious instructions are embedded in content the model retrieves — a web page, email, PDF, o... - [Inference](https://sureprompts.com/glossary/inference): Inference is the process of using a trained AI model to generate predictions or outputs from new inputs. - [Instruction Following](https://sureprompts.com/glossary/instruction-following): Instruction following is an AI model's ability to accurately understand and execute explicit directions given in a prompt — including format requirements, le... - [Instruction Tuning](https://sureprompts.com/glossary/instruction-tuning): Instruction tuning is a training technique where a pre-trained language model is further trained on a curated dataset of instruction-response pairs to improv... ### J - [Jailbreaking](https://sureprompts.com/glossary/jailbreaking): Jailbreaking refers to techniques used to bypass an AI model's built-in safety restrictions, content policies, and behavioral guidelines to produce outputs the model was trained to refuse. - [JSON Mode](https://sureprompts.com/glossary/json-mode): JSON mode is a model configuration setting that constrains the AI's output to be valid, parseable JSON. ### K - [Knowledge Cutoff](https://sureprompts.com/glossary/knowledge-cutoff): A knowledge cutoff is the date beyond which an AI model has no training data, meaning it cannot answer questions about events, discoveries, or changes that occurred after that point. - [Knowledge Graph](https://sureprompts.com/glossary/knowledge-graph): A knowledge graph is a structured database that represents real-world entities (people, places, concepts) and the relationships between them as an interconnected network of nodes and edges. - [KV-Cache](https://sureprompts.com/glossary/kv-cache): A KV-cache (key-value cache) stores the computed attention key and value matrices from previously processed tokens so the model does not need to recalculate them when generating each new token. ### L - [LangGraph](https://sureprompts.com/glossary/langgraph): LangGraph is an open-source Python library from the LangChain team for building stateful, multi-actor LLM applications as graphs. - [Large Language Model (LLM)](https://sureprompts.com/glossary/llm): A large language model (LLM) is an AI system trained on massive amounts of text data that can understand, generate, and reason about natural language. - [Latent Space](https://sureprompts.com/glossary/latent-space): Latent space is the high-dimensional internal representation space where AI models encode the meaning, relationships, and features of input data as numerical vectors. - [Least-to-Most Prompting](https://sureprompts.com/glossary/least-to-most-prompting): Least-to-most prompting is a reasoning pattern in which the model first decomposes a complex problem into an ordered sequence of easier sub-problems, then so... - [Letta](https://sureprompts.com/glossary/letta): Letta is an open-source stateful agent framework where the agent itself manages its memory via tool calls. - [LLM-as-Judge](https://sureprompts.com/glossary/llm-as-judge): LLM-as-judge is an evaluation pattern in which an LLM scores the outputs of another model against a rubric. - [Logits](https://sureprompts.com/glossary/logits): Logits are the raw, unnormalized numerical scores that a language model assigns to each token in its vocabulary as the potential next token. - [Long-Term Memory (Agent Memory)](https://sureprompts.com/glossary/long-term-memory): Long-term memory is a persistent store that gives an agent access to information across sessions — user preferences, prior decisions, past tool results worth... - [LoRA (Low-Rank Adaptation)](https://sureprompts.com/glossary/lora): LoRA (Low-Rank Adaptation) is a parameter-efficient fine-tuning technique that adapts a pre-trained AI model to new tasks by injecting small trainable matric... - [Lost in the Middle](https://sureprompts.com/glossary/lost-in-the-middle): Lost in the middle is the finding from Liu et al. ### M - [Many-Shot Jailbreaking](https://sureprompts.com/glossary/many-shot-jailbreaking): Many-shot jailbreaking is a long-context attack pattern identified by Anthropic researchers in 2024. - [Mastra](https://sureprompts.com/glossary/mastra): Mastra is an open-source TypeScript framework for building AI agents and workflows. - [mem0](https://sureprompts.com/glossary/mem0): mem0 is an open-source memory layer that adds persistent memory to any LLM application via four primitives: add, search, update, delete. - [Memory Block](https://sureprompts.com/glossary/memory-block): A memory block is a labeled, persistent chunk of agent memory directly editable by the agent via tool calls. - [Memory Recall](https://sureprompts.com/glossary/memory-recall): Memory recall is the retrieval step in agent memory: surfacing relevant past memory into the current context window so the model can use it. - [Meta-Prompting](https://sureprompts.com/glossary/meta-prompting): Meta-prompting is the practice of using an AI model to generate, refine, or optimize prompts for other AI tasks. - [Mixture of Experts (MoE)](https://sureprompts.com/glossary/mixture-of-experts): Mixture of experts (MoE) is a neural network architecture that divides a model into many specialized sub-networks called "experts" and uses a routing mechani... - [Mixture of Prompts](https://sureprompts.com/glossary/mixture-of-prompts): Mixture of prompts is an ensembling pattern where the same input is run through several different prompts and the resulting outputs are combined — by majorit... - [Model Cascade](https://sureprompts.com/glossary/model-cascade): A model cascade is a routing pattern in which each request is first attempted by a cheaper, smaller model and only escalated to a stronger, more expensive mo... - [Model Collapse](https://sureprompts.com/glossary/model-collapse): Model collapse is a phenomenon where AI models progressively degrade when trained on data generated by other AI models rather than human-created content. - [Model Context Protocol (MCP)](https://sureprompts.com/glossary/mcp): The Model Context Protocol (MCP) is an open standard developed by Anthropic that provides a universal way to connect AI models to external data sources, tools, and services. - [Model Distillation](https://sureprompts.com/glossary/model-distillation): Model distillation is a technique for creating a smaller, more efficient "student" model that approximates the behavior of a larger "teacher" model. - [Model Routing](https://sureprompts.com/glossary/model-routing): Model routing is the practice of dispatching different requests to different language models based on task classification, cost target, or expected reasoning depth. - [Multi-Agent System](https://sureprompts.com/glossary/multi-agent-system): A multi-agent system is a system in which two or more LLM-driven agents collaborate on a task, typically by exchanging messages, handing off ownership, or be... - [Multi-Modal AI](https://sureprompts.com/glossary/multi-modal): Multi-modal AI refers to artificial intelligence systems that can process and generate content across multiple types of data — such as text, images, audio, and video — within a single model. - [Multi-Query Retrieval](https://sureprompts.com/glossary/multi-query-retrieval): Multi-query retrieval is a RAG pattern that hedges against the single-query-phrasing failure mode of standard retrieval. - [Multimodal Prompting](https://sureprompts.com/glossary/multimodal-prompting): Multimodal prompting is the practice of combining multiple input types — such as text, images, audio, or video — within a single prompt to give an AI model richer context for its response. - [Multimodal RAG](https://sureprompts.com/glossary/multimodal-rag): Multimodal RAG is a retrieval-augmented-generation variant in which the indexed corpus and the retrieval step span multiple modalities — text, images, tables... ### N - [Needle in a Haystack](https://sureprompts.com/glossary/needle-in-a-haystack): Needle in a haystack is a long-context evaluation pattern that measures whether a model can retrieve a specific fact (the needle) planted at an arbitrary pos... - [Negative Prompting](https://sureprompts.com/glossary/negative-prompting): Negative prompting is a technique where you explicitly tell the AI model what to avoid, exclude, or not do in its response. ### O - [OpenAI Agents SDK](https://sureprompts.com/glossary/openai-agents-sdk): The OpenAI Agents SDK is OpenAI's official Python framework for building production-grade agents. - [OSWorld](https://sureprompts.com/glossary/osworld): OSWorld is an agent evaluation benchmark for desktop and browser computer-use tasks. - [Output Parsing](https://sureprompts.com/glossary/output-parsing): Output parsing is the process of extracting structured, machine-readable data from an AI model's free-form text responses. ### P - [Parent-Document Retrieval](https://sureprompts.com/glossary/parent-document-retrieval): Parent-document retrieval is a chunking-and-retrieval pattern that separates the unit used for matching from the unit used for generation. - [Perplexity](https://sureprompts.com/glossary/perplexity-metric): Perplexity is a standard metric for evaluating how well a language model predicts a sequence of text. - [Persona Prompting](https://sureprompts.com/glossary/persona-prompting): Persona prompting is a technique where you ask the AI to adopt a specific identity, personality, or character to shape the tone, vocabulary, and perspective of its responses. - [Plan-and-Execute Prompting](https://sureprompts.com/glossary/plan-and-execute): Plan-and-execute prompting is a two-phase agent pattern. - [Prefix-Tuning](https://sureprompts.com/glossary/prefix-tuning): Prefix-tuning is a parameter-efficient fine-tuning method in which a small set of continuous, trainable vectors — the "prefix" — is prepended to the input at... - [Procedural Memory](https://sureprompts.com/glossary/procedural-memory): Procedural memory is memory of how to do something — implicit knowledge tied to learned routines and skills. - [Program of Thoughts](https://sureprompts.com/glossary/program-of-thoughts): Program of thoughts is a reasoning technique in which the model generates code — typically Python — to solve a numerical or logical problem, then executes the code to obtain the answer. - [Prompt Caching](https://sureprompts.com/glossary/prompt-caching): Prompt caching is a performance optimization where the model's computed internal representations (key-value attention states) of a static prompt prefix are stored and reused across multiple requests. - [Prompt Chaining](https://sureprompts.com/glossary/prompt-chaining): Prompt chaining is a strategy where you break a complex task into a sequence of simpler prompts, feeding the output of one step as input to the next. - [Prompt Compression](https://sureprompts.com/glossary/prompt-compression): Prompt compression encompasses techniques for reducing the length of a prompt while preserving its essential meaning and effectiveness. - [Prompt Engineering](https://sureprompts.com/glossary/prompt-engineering): Prompt engineering is the practice of designing, refining, and optimizing the text inputs (prompts) given to AI models to elicit the most useful, accurate, and relevant outputs. - [Prompt Ensembling](https://sureprompts.com/glossary/prompt-ensembling): Prompt ensembling is a technique that runs multiple variations of a prompt for the same task and combines their outputs to produce a more accurate and robust final result. - [Prompt Injection](https://sureprompts.com/glossary/prompt-injection): Prompt injection is a security vulnerability where a malicious user crafts input that overrides or manipulates the AI model's original instructions, causing ... - [Prompt Injection Defense](https://sureprompts.com/glossary/prompt-injection-defense): Prompt injection defense refers to the techniques and strategies used to protect AI systems from prompt injection attacks, where malicious inputs attempt to override the model's original instructions. - [Prompt Leaking](https://sureprompts.com/glossary/prompt-leaking): Prompt leaking is an attack technique where a user crafts inputs designed to trick an AI model into revealing its hidden system prompt or confidential instructions. - [Prompt Observability](https://sureprompts.com/glossary/prompt-observability): Prompt observability is the operational practice of logging, tracing, and monitoring prompt inputs, outputs, and model behavior in production. - [Prompt Optimization](https://sureprompts.com/glossary/prompt-optimization): Prompt optimization is the systematic process of iteratively refining prompts to improve the quality, accuracy, and consistency of AI model outputs. - [Prompt Routing](https://sureprompts.com/glossary/prompt-routing): Prompt routing is the practice of automatically directing each user prompt to the most suitable AI model based on task type, complexity, and cost constraints. - [Prompt Template](https://sureprompts.com/glossary/prompt-template): A prompt template is a reusable, pre-structured prompt with placeholder variables that can be filled in with specific details for each use. - [Prompt Tuning](https://sureprompts.com/glossary/prompt-tuning): Prompt tuning is a parameter-efficient technique that adapts a large language model to specific tasks by training small learnable vectors called "soft prompts" that are prepended to the input. - [Prompt Versioning](https://sureprompts.com/glossary/prompt-versioning): Prompt versioning is the practice of tracking changes to prompts over time using version control principles — assigning version identifiers, recording modifi... - [Prosody](https://sureprompts.com/glossary/prosody): Prosody is the rhythm, stress, intonation, and pacing of speech — the suprasegmental layer above individual phonemes that carries emotion, emphasis, question vs. ### Q - [Quantization](https://sureprompts.com/glossary/quantization): Quantization is a technique that reduces an AI model's numerical precision — for example, converting 16-bit floating-point weights to 4-bit integers — to shr... - [Query Rewriting](https://sureprompts.com/glossary/query-rewriting): Query rewriting is a retrieval preprocessing step that transforms the user's question before it is sent to the retriever. ### R - [RAFT (Retrieval-Augmented Fine-Tuning)](https://sureprompts.com/glossary/raft): RAFT is a training technique that combines retrieval-augmented generation with fine-tuning. - [RAGAS](https://sureprompts.com/glossary/ragas): RAGAS is an open-source evaluation framework for retrieval-augmented generation systems. - [RCAF Prompt Structure](https://sureprompts.com/glossary/rcaf): RCAF is a 4-part prompt skeleton — Role, Context, Action, Format — for drafting maintainable AI prompts. - [ReAct Prompting](https://sureprompts.com/glossary/react-prompting): ReAct prompting is a technique that interleaves Reasoning and Acting: the model writes a short reasoning trace about what to do next, takes an action (typica... - [Realtime Voice API](https://sureprompts.com/glossary/realtime-voice-api): A realtime voice API is a speech-to-speech architecture that accepts streaming audio input and returns streaming audio output directly, without the classical STT-then-LLM-then-TTS pipeline. - [Reasoning Model](https://sureprompts.com/glossary/reasoning-model): A reasoning model is an AI system specifically trained to perform extended, step-by-step thinking before producing a final answer. - [Reciprocal Rank Fusion (RRF)](https://sureprompts.com/glossary/reciprocal-rank-fusion): Reciprocal Rank Fusion is a technique for merging several ranked result lists — produced by different retrievers over the same corpus — into a single unified ranking. - [Red Teaming](https://sureprompts.com/glossary/red-teaming): Red teaming in AI is the practice of systematically probing an AI system for vulnerabilities, failure modes, and harmful behaviors through adversarial testing. - [Reflexion Prompting](https://sureprompts.com/glossary/reflexion): Reflexion is an agent prompting pattern in which, after a failed attempt, the agent generates a short verbal reflection on what went wrong and uses that refl... - [Reinforcement Learning from Human Feedback (RLHF)](https://sureprompts.com/glossary/reinforcement-learning-from-human-feedback): Reinforcement learning from human feedback (RLHF) is a training method where human evaluators rank or score multiple AI outputs, and those preferences are us... - [Reranking](https://sureprompts.com/glossary/reranking): Reranking is a secondary scoring pass over an initial set of retrieval candidates to improve their ordering before they are handed to the generator. - [Retrieval-Augmented Generation (RAG)](https://sureprompts.com/glossary/rag): Retrieval-augmented generation (RAG) is an architecture that enhances AI model responses by first retrieving relevant information from an external knowledge ... - [ReWOO (Reasoning WithOut Observation)](https://sureprompts.com/glossary/rewoo): ReWOO is an agent architecture that separates planning from execution. - [RLAIF (Reinforcement Learning from AI Feedback)](https://sureprompts.com/glossary/rlaif): RLAIF is a training technique that uses AI-generated preferences — typically from a strong LLM acting as a judge — to guide reinforcement-learning fine-tunin... - [Role Prompting](https://sureprompts.com/glossary/role-prompting): Role prompting is a technique where you assign the AI model a specific professional role or area of expertise to shape the depth, vocabulary, and perspective of its responses. - [RULER (Long-Context Benchmark)](https://sureprompts.com/glossary/ruler-benchmark): RULER is a long-context evaluation that goes beyond simple needle-in-a-haystack retrieval. ### S - [Sampling](https://sureprompts.com/glossary/sampling): Sampling is the process of selecting the next token from the probability distribution a language model produces at each generation step. - [Self-Ask Prompting](https://sureprompts.com/glossary/self-ask-prompting): Self-ask prompting is a reasoning pattern in which the model explicitly asks itself follow-up questions before answering a composite question. - [Self-Consistency](https://sureprompts.com/glossary/self-consistency): Self-consistency is a prompting strategy where you generate multiple responses to the same question using chain-of-thought reasoning, then select the most common answer among them. - [Self-Critique Prompting](https://sureprompts.com/glossary/self-critique): Self-critique prompting is a pattern where the model is asked to evaluate its own output against specific criteria, surface weaknesses, and suggest improveme... - [Self-Debug Prompting](https://sureprompts.com/glossary/self-debug): Self-debug prompting is a pattern in which the model generates code, an interpreter executes it, and the model receives the execution result — error messages... - [Self-RAG](https://sureprompts.com/glossary/self-rag): Self-RAG is a pattern in which the language model emits special reflection tokens that control its own retrieval and generation decisions. - [Self-Refine Prompting](https://sureprompts.com/glossary/self-refine): Self-refine prompting is an iterative pattern in which the model generates an output, critiques its own output against specified criteria, then produces a revised version. - [Self-Reflection](https://sureprompts.com/glossary/self-reflection): Self-reflection is a prompting technique where an AI model evaluates, critiques, and improves its own output in one or more follow-up steps. - [Semantic Caching](https://sureprompts.com/glossary/semantic-caching): Semantic caching is a pattern for caching LLM responses keyed by meaning similarity rather than exact prompt match. - [Semantic Memory](https://sureprompts.com/glossary/semantic-memory): Semantic memory is memory of general facts independent of when or how they were learned. - [Semantic Router](https://sureprompts.com/glossary/semantic-router): A semantic router is an embedding-based routing layer that classifies an incoming query to one of several downstream prompts, agents, tools, or models by com... - [Semantic Search](https://sureprompts.com/glossary/semantic-search): Semantic search is an information retrieval approach that finds results based on the meaning of a query rather than exact keyword matches. - [Semantic Similarity](https://sureprompts.com/glossary/semantic-similarity): Semantic similarity is a measure of how close two pieces of text are in meaning, regardless of whether they share the same words. - [Skeleton of Thought](https://sureprompts.com/glossary/skeleton-of-thought): Skeleton of thought is a reasoning pattern in which the model first produces a compact skeleton of the answer — a list of points or an outline — and then exp... - [Speaker Diarization](https://sureprompts.com/glossary/speaker-diarization): Speaker diarization is the "who spoke when" task: segmenting a multi-speaker audio recording by speaker identity and attaching speaker labels to each transcript segment. - [Spec-Driven Development](https://sureprompts.com/glossary/spec-driven-development): Spec-driven development is a workflow in which a written specification — acceptance criteria, edge cases, interfaces, validation rules, and explicit non-goal... - [Speech to Text (STT)](https://sureprompts.com/glossary/speech-to-text): Speech to text, or STT — also called automatic speech recognition (ASR) — is the transcription of spoken audio into written text. - [Step-Back Prompting](https://sureprompts.com/glossary/step-back-prompting): Step-back prompting is a technique in which the model first generates a higher-level abstraction, principle, or generalization — a "step back" from the specific question — before answering. - [Stop Sequence](https://sureprompts.com/glossary/stop-sequence): A stop sequence is a predefined token, string, or pattern that signals the AI model to immediately stop generating text when encountered in the output. - [Structured Decoding](https://sureprompts.com/glossary/structured-decoding): Structured decoding is an inference-time technique that constrains the model's output to conform to a grammar, regular expression, or JSON schema by masking invalid tokens at each generation step. - [Structured Output](https://sureprompts.com/glossary/structured-output): Structured output refers to AI model responses that follow a specific, machine-readable format such as JSON, XML, CSV, or a defined schema. - [SurePrompts Quality Rubric](https://sureprompts.com/glossary/sureprompts-quality-rubric): The SurePrompts Quality Rubric is a 7-dimension scoring framework for evaluating prompt quality: role clarity, context sufficiency, instruction specificity, ... - [Swarm](https://sureprompts.com/glossary/swarm): Swarm is an experimental cookbook framework released by OpenAI in 2024 that demonstrated lightweight multi-agent patterns — primarily handoffs and shared con... - [SWE-Bench](https://sureprompts.com/glossary/swe-bench): SWE-Bench is an evaluation benchmark from Princeton and the University of Washington that measures an AI agent's ability to resolve real GitHub issues by pro... - [Synthetic Data](https://sureprompts.com/glossary/synthetic-data): Synthetic data is artificially generated data created by AI models or algorithmic processes rather than collected from real-world events. - [System Prompt](https://sureprompts.com/glossary/system-prompt): A system prompt is a special set of instructions provided to an AI model before the user's message that defines the model's behavior, personality, constraint... ### T - [Tau-bench](https://sureprompts.com/glossary/tau-bench): Tau-bench is an agent evaluation benchmark that tests tool-use accuracy across multi-turn customer-service-style tasks. - [Temperature](https://sureprompts.com/glossary/temperature): Temperature is a parameter that controls the randomness and creativity of an AI model's output. - [Terminal-Bench](https://sureprompts.com/glossary/terminal-bench): Terminal-Bench is an evaluation benchmark for AI agents that measures their ability to complete long-horizon, multi-step shell tasks — git operations, build ... - [Test-Time Compute](https://sureprompts.com/glossary/test-time-compute): Test-time compute is the practice of allocating additional computational resources during inference — when the model generates a response — rather than during training. - [Text to Speech (TTS)](https://sureprompts.com/glossary/text-to-speech): Text to speech, or TTS, is the synthesis of spoken audio from written text. - [Thinking Model](https://sureprompts.com/glossary/thinking-model): A thinking model is an AI system that uses extended inference-time computation to reason through problems before producing a final answer. - [Token](https://sureprompts.com/glossary/token): A token is the basic unit of text that AI models use to process and generate language. - [Tokenizer](https://sureprompts.com/glossary/tokenizer): A tokenizer is the component that converts raw text into a sequence of tokens (numerical IDs) that an AI model can process, and converts model output tokens back into readable text. - [Tool Choice](https://sureprompts.com/glossary/tool-choice): Tool choice is an API parameter on modern tool-calling models that controls whether and how the model selects a tool. - [Tool Use (Function Calling)](https://sureprompts.com/glossary/tool-use): Tool use, also called function calling, is the ability of an AI model to invoke external tools, APIs, or functions during a conversation to perform actions beyond text generation. - [Top-P (Nucleus Sampling)](https://sureprompts.com/glossary/top-p): Top-P, also known as nucleus sampling, is a parameter that controls which tokens the model considers when generating each word. - [Transfer Learning](https://sureprompts.com/glossary/transfer-learning): Transfer learning is a machine learning technique where a model trained on one task or dataset is reused as the starting point for a different but related task. - [Transformer](https://sureprompts.com/glossary/transformer): A transformer is the neural network architecture that powers virtually all modern large language models, including GPT, Claude, Gemini, and LLaMA. - [Tree of Thought Prompting](https://sureprompts.com/glossary/tree-of-thought): Tree of thought prompting is an advanced reasoning technique where the AI model explores multiple branching solution paths simultaneously, evaluates each bra... ### V - [Vector Database](https://sureprompts.com/glossary/vector-database): A vector database is a specialized database designed to store, index, and efficiently query high-dimensional embedding vectors. - [Vector Memory](https://sureprompts.com/glossary/vector-memory): Vector memory is agent memory stored as embedding vectors in a vector database, retrieved by semantic similarity. - [Vibe Coding](https://sureprompts.com/glossary/vibe-coding): Vibe coding is a term popularized by Andrej Karpathy in early 2025 for a mode of working with AI coding agents in which the developer iterates by describing ... - [Vision-Language Model (VLM)](https://sureprompts.com/glossary/vision-language-model): A vision-language model (VLM) is an AI system that can process, understand, and reason about both visual inputs (images, screenshots, diagrams) and text simu... - [Voice Cloning](https://sureprompts.com/glossary/voice-cloning): Voice cloning is the synthesis of a target speaker's voice from a short reference audio sample, allowing a TTS system to produce new speech in that speaker's... - [Voice Prompting](https://sureprompts.com/glossary/voice-prompting): Voice prompting is the practice of writing prompts for realtime voice and audio AI interfaces — speech-to-speech systems, voice agents, and realtime APIs — w... ### W - [Working Memory](https://sureprompts.com/glossary/working-memory): Working memory is short-term active memory that holds the current task context. ### X - [xAI](https://sureprompts.com/glossary/xai): xAI is the artificial intelligence research company founded by Elon Musk in 2023. ### Z - [Zero-Shot Chain of Thought](https://sureprompts.com/glossary/zero-shot-chain-of-thought): Zero-shot chain of thought is a prompting technique where you append a simple phrase like "Let's think step by step" to a question without providing any reasoning examples. - [Zero-Shot Prompting](https://sureprompts.com/glossary/zero-shot-prompting): Zero-shot prompting is the simplest prompting approach where you give the AI model a task instruction without providing any examples. ## Optional - [SurePrompts Blog](https://sureprompts.com/blog): Full archive of prompt engineering articles, model comparisons, and AI workflow guides. - [Glossary index](https://sureprompts.com/glossary): Searchable glossary of prompting techniques, model architecture, evaluation, and AI safety concepts. - [Template Library](https://sureprompts.com/templates): Browse the full catalog of 350+ guided prompt templates organized by use case and model. - [Full content corpus](https://sureprompts.com/llms-full.txt): Machine-readable full text of all canonical content plus tutorial / glossary / template indexes.