# AI & Tech Glossary - Lumeor Studio > Explore our comprehensive glossary of Artificial Intelligence, Automation, and Software Development terms. Understand the technology driving your business forward. # AI & Tech Glossary Deciphering the language of innovation. A comprehensive guide to the terms shaping the future of business. ## AI [ ### Agentic AI Agentic AI describes AI systems that pursue a goal across multiple steps instead of answering a sing... Read Definition →](https://www.lumeor.studio/glossary/agentic-ai/)[ ### AI Agent An AI agent is software that uses a large language model to work toward a goal by deciding which act... Read Definition →](https://www.lumeor.studio/glossary/ai-agent/)[ ### Custom AI Agents Custom AI agents are AI agents built for one organization's specific processes, systems and rules, r... Read Definition →](https://www.lumeor.studio/glossary/custom-ai-agents/)[ ### Multi-Agent System A multi-agent system is an AI application in which several specialized agents work together on a tas... Read Definition →](https://www.lumeor.studio/glossary/multi-agent-system/)[ ### LLM (Large Language Model) A large language model (LLM) is a neural network trained on very large amounts of text to predict th... Read Definition →](https://www.lumeor.studio/glossary/llm-large-language-model/)[ ### RAG (Retrieval-Augmented Generation) Retrieval-augmented generation (RAG) is a technique where an AI system first searches a set of trust... Read Definition →](https://www.lumeor.studio/glossary/rag-retrieval-augmented-generation/)[ ### Tool Calling (Function Calling) Tool calling, also called function calling, is a language model capability in which the model respon... Read Definition →](https://www.lumeor.studio/glossary/tool-calling/)[ ### MCP (Model Context Protocol) The Model Context Protocol (MCP) is an open standard, introduced by Anthropic in 2024 and donated to... Read Definition →](https://www.lumeor.studio/glossary/mcp-model-context-protocol/)[ ### Structured Outputs Structured outputs are model responses constrained to a defined format, usually a JSON schema with n... Read Definition →](https://www.lumeor.studio/glossary/structured-outputs/)[ ### Prompt Engineering Prompt engineering is the practice of designing the instructions, context and examples given to a la... Read Definition →](https://www.lumeor.studio/glossary/prompt-engineering/)[ ### System Prompt A system prompt is the set of standing instructions an application gives a language model before any... Read Definition →](https://www.lumeor.studio/glossary/system-prompt/)[ ### Context Window A context window is the maximum amount of text, measured in tokens, that a language model can proces... Read Definition →](https://www.lumeor.studio/glossary/context-window/)[ ### Token A token is the unit of text a language model reads and writes, usually a word, part of a word or a p... Read Definition →](https://www.lumeor.studio/glossary/token/)[ ### Embeddings Embeddings are lists of numbers (vectors) that represent the meaning of a piece of text, an image or... Read Definition →](https://www.lumeor.studio/glossary/embeddings/)[ ### Vector Database A vector database stores embeddings alongside the original content and its metadata, and quickly fin... Read Definition →](https://www.lumeor.studio/glossary/vector-database/)[ ### Chunking Chunking is the step in building a retrieval system where long documents are split into smaller pass... Read Definition →](https://www.lumeor.studio/glossary/chunking/)[ ### Knowledge Base A knowledge base is an organized collection of information a business uses to answer questions and d... Read Definition →](https://www.lumeor.studio/glossary/knowledge-base/)[ ### Hallucination A hallucination is output from an AI model that is fluent and confident but false or unsupported, su... Read Definition →](https://www.lumeor.studio/glossary/hallucination/)[ ### Grounding Grounding is the practice of tying an AI model's output to specific, verifiable sources, such as ret... Read Definition →](https://www.lumeor.studio/glossary/grounding/)[ ### Guardrails Guardrails are the controls placed around an AI system to keep its inputs, outputs and actions withi... Read Definition →](https://www.lumeor.studio/glossary/guardrails/)[ ### Prompt Injection Prompt injection is an attack in which text supplied to an AI system, either typed by a user or hidd... Read Definition →](https://www.lumeor.studio/glossary/prompt-injection/)[ ### Evaluation (Evals) Evaluations, or evals, are repeatable tests that measure how well an AI system performs a task, usin... Read Definition →](https://www.lumeor.studio/glossary/evals-ai-evaluation/)[ ### Human in the Loop Human in the loop is a design pattern where a person reviews, approves or corrects an AI system's ou... Read Definition →](https://www.lumeor.studio/glossary/human-in-the-loop/)[ ### Fine-Tuning Fine-tuning is the process of further training an existing language model on a set of example inputs... Read Definition →](https://www.lumeor.studio/glossary/fine-tuning/)[ ### Inference Inference is the process of running a trained AI model to produce an output, such as generating a re... Read Definition →](https://www.lumeor.studio/glossary/inference/)[ ### Latency Latency is the time between sending a request and receiving a response. In AI systems it includes ne... Read Definition →](https://www.lumeor.studio/glossary/latency/)[ ### Model Routing Model routing is the practice of sending each AI request to the most suitable model based on task di... Read Definition →](https://www.lumeor.studio/glossary/model-routing/)[ ### Prompt Caching Prompt caching is a feature offered by some model providers that stores the processed form of a repe... Read Definition →](https://www.lumeor.studio/glossary/prompt-caching/)[ ### Chatbot A chatbot is software that holds a text conversation with users, typically on a website, in an app o... Read Definition →](https://www.lumeor.studio/glossary/chatbot/)[ ### Voice AI Agent A voice AI agent is an AI system that holds spoken conversations, usually over the phone, to answer ... Read Definition →](https://www.lumeor.studio/glossary/voice-ai-agent/)[ ### Speech-to-Text (STT) Speech-to-text (STT), also called automatic speech recognition, is technology that converts spoken a... Read Definition →](https://www.lumeor.studio/glossary/speech-to-text/)[ ### Text-to-Speech (TTS) Text-to-speech (TTS) is technology that converts written text into spoken audio. Modern neural TTS p... Read Definition →](https://www.lumeor.studio/glossary/text-to-speech/)[ ### OCR (Optical Character Recognition) Optical character recognition (OCR) is technology that converts images of text, such as scanned docu... Read Definition →](https://www.lumeor.studio/glossary/ocr-optical-character-recognition/) ## Automation [ ### Business Process Automation (BPA) Business process automation (BPA) is the use of software to run a multi-step business process with l... Read Definition →](https://www.lumeor.studio/glossary/business-process-automation/)[ ### Workflow Automation Workflow automation is the use of software to run a sequence of tasks automatically when a trigger o... Read Definition →](https://www.lumeor.studio/glossary/workflow-automation/)[ ### n8n n8n is a workflow automation platform that connects apps, APIs and databases through a visual, node-... Read Definition →](https://www.lumeor.studio/glossary/n8n-workflow-automation/)[ ### iPaaS (Integration Platform as a Service) An integration platform as a service (iPaaS) is a cloud platform for connecting applications and dat... Read Definition →](https://www.lumeor.studio/glossary/ipaas-integration-platform-as-a-service/)[ ### Webhook A webhook is an automated HTTP request that one application sends to a URL you specify when a partic... Read Definition →](https://www.lumeor.studio/glossary/webhook/)[ ### RPA (Robotic Process Automation) Robotic process automation (RPA) is software that automates tasks by mimicking how a person uses app... Read Definition →](https://www.lumeor.studio/glossary/rpa-robotic-process-automation/)[ ### Intelligent Document Processing (IDP) Intelligent document processing (IDP) is the automated capture, classification and extraction of dat... Read Definition →](https://www.lumeor.studio/glossary/intelligent-document-processing/)[ ### ETL (Extract, Transform, Load) ETL (extract, transform, load) is a data integration process that pulls data from source systems, cl... Read Definition →](https://www.lumeor.studio/glossary/etl-extract-transform-load/) ## Development [ ### API (Application Programming Interface) An application programming interface (API) is a defined way for one piece of software to request dat... Read Definition →](https://www.lumeor.studio/glossary/api-application-programming-interface/)[ ### OAuth OAuth is an open authorization standard, now mostly used in its OAuth 2.0 form, that lets a user gra... Read Definition →](https://www.lumeor.studio/glossary/oauth/)[ ### Rate Limiting Rate limiting is a control that caps how many requests a client can make to an API within a period o... Read Definition →](https://www.lumeor.studio/glossary/rate-limiting/)[ ### Idempotency Idempotency is the property of an operation that produces the same result whether it runs once or se... Read Definition →](https://www.lumeor.studio/glossary/idempotency/)[ ### Observability Observability is the ability to understand what a software system is doing from the data it emits, s... Read Definition →](https://www.lumeor.studio/glossary/observability/)[ ### Self-Hosting Self-hosting means running software on infrastructure you control, such as your own servers or a pri... Read Definition →](https://www.lumeor.studio/glossary/self-hosting/)[ ### MVP (Minimum Viable Product) A minimum viable product (MVP) is the smallest version of a product that real users can use to get i... Read Definition →](https://www.lumeor.studio/glossary/mvp-minimum-viable-product/)[ ### React Native React Native is an open-source framework, created at Meta (then Facebook) and now owned by the indep... Read Definition →](https://www.lumeor.studio/glossary/react-native-development/)[ ### Next.js Next.js is an open-source React framework, maintained by Vercel, for building websites and web appli... Read Definition →](https://www.lumeor.studio/glossary/nextjs-development/) ## Strategy [ ### Generative AI Strategy A generative AI strategy is a company's plan for where and how it will use generative AI, such as la... Read Definition →](https://www.lumeor.studio/glossary/generative-ai-strategy/)[ ### Digital Transformation Digital transformation is the process of changing how a business operates and serves customers by re... Read Definition →](https://www.lumeor.studio/glossary/digital-transformation/)[ ### AI Governance AI governance is the set of policies, roles and processes an organization uses to decide how AI may ... Read Definition →](https://www.lumeor.studio/glossary/ai-governance/)[ ### AI Readiness Assessment An AI readiness assessment is a structured review of how prepared an organization is to adopt AI, co... Read Definition →](https://www.lumeor.studio/glossary/ai-readiness-assessment/)[ ### Proof of Concept (POC) A proof of concept (POC) is a small, time-boxed project that tests whether a specific technical appr... Read Definition →](https://www.lumeor.studio/glossary/proof-of-concept/)[ ### AI TCO (Total Cost of Ownership) AI total cost of ownership (TCO) is the full cost of an AI system over its useful life, not just the... Read Definition →](https://www.lumeor.studio/glossary/ai-tco-total-cost-of-ownership/)[ ### Data Residency Data residency refers to the geographic location where data is stored and processed, and to requirem... Read Definition →](https://www.lumeor.studio/glossary/data-residency/)[ ### BAA (Business Associate Agreement) A Business Associate Agreement (BAA) is a contract required under HIPAA between a covered entity, su... Read Definition →](https://www.lumeor.studio/glossary/baa-business-associate-agreement/)[ ### Zero Data Retention (ZDR) Zero data retention (ZDR) is an arrangement with an AI model provider under which prompts and output... Read Definition →](https://www.lumeor.studio/glossary/zero-data-retention/)[ ### Fractional AI Officer A fractional AI officer is an experienced AI leader who works part-time for a company, often on a mo... Read Definition →](https://www.lumeor.studio/glossary/fractional-ai-officer/) --- Source: https://www.lumeor.studio/glossary/