Agentic AI refers to artificial intelligence systems that can independently plan, make decisions, use tools and carry out multi-step tasks to achieve a goal. Unlike AI that only responds to a prompt, agentic AI takes actions in software, checks the results and adapts its approach, usually within limits and approval points set by people.
An agentic workflow is a structured business process in which AI agents carry out some or all of the steps, deciding how to complete each one, using tools and passing results along, while people set the goals and approve key decisions. It combines the flexibility of AI agents with the predictability of a defined process.
An AI agent is a software system that uses artificial intelligence, usually a large language model, to pursue a goal on a user's behalf. It can break a task into steps, use tools such as search, databases or business applications, act on what it finds, and adjust its plan until the goal is met or a person needs to step in.
AI automation is the use of artificial intelligence to automate business tasks that require some judgement, such as reading documents, understanding messages, classifying requests, making predictions or drafting responses. It extends traditional rule-based automation to work with unstructured information like emails, PDFs, images and conversations.
Artificial intelligence (AI) is the field of computer science that builds systems able to perform tasks that normally require human intelligence, such as understanding language, recognising images, finding patterns in data, making predictions and taking decisions. Modern AI systems learn these abilities from data rather than following only hand-written rules.
Generative AI is a type of artificial intelligence that creates new content, including text, images, code, audio and video, based on patterns learned from large amounts of training data. Users usually guide it with a prompt written in plain language, and the system produces an original output rather than selecting from existing answers.
A large language model (LLM) is an AI model trained on very large amounts of text to understand and generate human language. It predicts the most likely next piece of text given what came before, which lets it answer questions, summarise documents, translate, write code and follow instructions. Well-known examples include the models behind ChatGPT, Claude and Gemini.
Machine learning (ML) is a branch of artificial intelligence in which computer systems learn patterns from data and use them to make predictions or decisions, without being explicitly programmed with every rule. The more relevant examples a model sees, the better it can generalise to new cases it has not encountered before.
Natural language processing (NLP) is the field of artificial intelligence that enables computers to understand, interpret and generate human language, in both text and speech. It powers tasks such as translation, sentiment analysis, document classification, information extraction, chatbots and voice assistants.
Retrieval-augmented generation (RAG) is a technique in which an AI system first retrieves relevant information from a trusted source, such as company documents or a database, and then passes it to a large language model to generate the answer. This grounds responses in current, specific facts and lets the system show where an answer came from.