AI & Automation
AI and automation use software to generate, interpret, classify, retrieve, or act on information and to reduce repetitive work across digital systems.
Terms
AI & Automation
AI and automation use software to interpret, generate, classify, retrieve, or act on information and to automate work across digital systems.
AI Agent
An AI agent is a system that uses an AI model to plan or decide how to complete multi-step work, often with access to tools or external systems.
AI Evaluation (Eval)
AI evaluation is the systematic testing of an AI system against defined examples and criteria to determine whether it performs its intended task reliably enough.
AI Model
An AI model is a trained computational system that transforms inputs into predictions, classifications, generated content, or other outputs.
Artificial Intelligence (AI)
Artificial intelligence is a broad category of computer systems designed to perform tasks involving capabilities such as prediction, classification, perception, language processing, generation, or planning.
Context Window
A context window is the amount of information an AI model can consider within its active input and output context, commonly measured in tokens.
Embedding
An embedding is a numerical representation of information that allows semantic similarity and relatedness to be compared mathematically.
Fine-Tuning
Fine-tuning further trains an existing AI model on additional examples to adapt its behaviour to a particular task or pattern.
Generative AI
Generative AI is artificial intelligence designed to create new content such as text, images, audio, video, code, or structured information.
Hallucination
A hallucination is AI-generated content that presents false, unsupported, invented, or internally inconsistent information as though it were valid.
Human-in-the-Loop (HITL)
Human-in-the-loop is a system design where a person intentionally reviews, approves, corrects, or supervises part of an AI or automated workflow.
Large Language Model (LLM)
A large language model is an AI model trained to process and generate language by predicting and working with sequences of tokens.
Prompt
A prompt is input provided to an AI model that supplies instructions, context, examples, source material, or other information used to guide its response.
Prompt Injection
Prompt injection is an attack or failure mode where untrusted input attempts to manipulate an AI model's instructions or behaviour in unintended ways.
Retrieval-Augmented Generation (RAG)
Retrieval-Augmented Generation is a pattern where relevant external information is retrieved and supplied to a generative model when producing a response.
Rule-Based Automation
Rule-based automation performs predefined actions according to explicit conditions rather than relying on an AI model to interpret the next step.
Token
A token is a unit of information used by a language model to represent and process its input and generated output.
Tool Use / Function Calling
Tool use or function calling allows an AI model to request defined external functions that retrieve information or perform actions outside the model itself.
Vector Database
A vector database is a data system designed to store and search numerical vector representations such as embeddings for similarity and semantic retrieval.
Workflow Automation
Workflow automation uses software to coordinate recurring tasks through defined triggers, rules, and actions, with or without AI.