OutSystems AI Glossary

Agent builder

An agent builder is a tool used to create, configure, and deploy AI agents that can perform tasks, make decisions, and interact with systems or users.

Agent builders typically include visual development environments, integrations, and orchestration capabilities. In enterprise settings, an AI agent builder enables teams to design agents with governance, scalability, and security in mind, supporting production-ready AI systems.

Agent memory

Agent memory is the ability of an AI agent to retain and use information from previous interactions, workflows, or connected systems.

Agent workflow memory can include conversation history, task context, or system data. In enterprise environments, AI agent memory must be managed with strong governance, access control, and compliance to ensure accuracy and data security.

Agent Workbench

Agent Workbench is a product offering within the OutSystems platform that enables teams to design, build, orchestrate, and govern custom AI agents within a unified development environment.

It enables agentic AI innovation by providing tools to create custom AI agents, define workflows, integrate enterprise systems, and apply governance controls across the full lifecycle of agent development.

Agentic AI

Agentic AI is a type of artificial intelligence that can autonomously plan, execute, and adapt tasks to achieve defined goals with minimal human input.

Agentic AI systems go beyond simple responses by reasoning through multi-step processes, interacting with tools, and coordinating actions. This makes them suitable for complex enterprise workflows and operational automation.

Agentic systems engineering

Agentic systems engineering is the practice of building, managing, and evolving systems for the enterprise. It combines an agentic development experience, governance, and lifecycle management to ensure agentic systems are reliable, scalable, and aligned with business outcomes.

OutSystems enables Agentic Systems Engineering, a new approach to enterprise AI development designed to help teams build, operate, and evolve governed agentic systems at scale. It allows organizations to build anywhere, natively with OutSystems or with their preferred agentic coding tools, while managing and governing from a single, unified platform.

Agentic workflows

Agentic workflows are structured processes where AI agents execute tasks, make decisions, and coordinate actions across systems to complete multi-step objectives.

An agentic AI workflow often includes triggers, decision logic, integrations, and human-in-the-loop checkpoints. These workflows are commonly used to automate complex enterprise operations.

Agents

AI agents are software entities that can perceive inputs, process information, and take actions to achieve specific goals.

AI agents explained simply: they act on behalf of users or systems, using data and logic to complete tasks. In enterprise environments, agents often integrate with existing systems and operate within defined governance frameworks.

AI platform

An AI platform is a software environment that enables teams to build, deploy, and manage AI applications and models.

An enterprise AI platform typically includes tools for development, integration, orchestration, monitoring, and governance, allowing organizations to scale AI initiatives across systems and teams.

AI aPaaS

AI aPaaS (AI platform as a service) is a cloud-based platform that provides tools and infrastructure to build, deploy, and manage AI applications without managing underlying hardware.

AI platform as a service solutions support faster development by offering prebuilt components, integrations, and scalable environments for AI workloads.

AI app builder

An AI app builder is a tool that enables users to create applications powered by artificial intelligence with minimal manual coding.

AI web app builders often include visual interfaces, prebuilt components, and AI capabilities such as automation, prediction, or natural language interaction, accelerating application development.

AI application generation

AI application generation is the process of using artificial intelligence to automatically create applications, components, or code based on user inputs.

AI app generators can produce functional applications faster by translating prompts, requirements, or data models into working software, reducing development time and effort.

AI assistants

AI assistants are software tools that help users complete tasks, answer questions, or automate workflows using artificial intelligence.

An AI assistant app can support activities such as writing, scheduling, analysis, or development, often integrating with enterprise systems to enhance productivity.

AI chatbot

An AI chatbot is a conversational interface that uses artificial intelligence to simulate human-like interactions with users.

AI chatbot development focuses on enabling chatbots to understand user intent, respond accurately, and integrate with backend systems for tasks such as support, transactions, or information retrieval.

AI copilots

AI copilots are intelligent assistants embedded within applications that help users perform tasks more efficiently.

An enterprise AI copilot can provide suggestions, automate steps, or generate content in real time, acting as a collaborative partner within workflows.

AI development

AI development is the process of designing, building, testing, and deploying artificial intelligence applications and systems.

AI app development includes model integration, data processing, workflow design, and governance, often supported by an AI development platform to accelerate delivery.

AI ethics

AI ethics refers to the principles and guidelines that ensure artificial intelligence systems are developed and used responsibly.

AI ethics and governance address issues such as bias, transparency, accountability, and data privacy, especially in enterprise and regulated environments.

AI-generated software

AI-generated software is code or applications created with the assistance of artificial intelligence tools.

This includes generating code, UI components, workflows, or entire applications based on prompts or inputs, enabling faster development while requiring validation and oversight.

AI model

An AI model is a mathematical system trained on data to recognize patterns, make predictions, or generate outputs.

Custom AI models can be tailored to specific business needs, while prebuilt models provide general capabilities such as language understanding or image recognition.

AI software

AI software refers to applications or systems that use artificial intelligence to perform tasks such as analysis, automation, or decision-making.

AI software development involves integrating models, data, and workflows into usable applications that deliver business value.

Artificial general intelligence

Artificial general intelligence (AGI) is a theoretical form of AI that can perform any intellectual task that a human can do.

AGI differs from current AI systems, which are specialized for specific tasks, and remains a long-term goal in AI research.

Autonomous AI

Autonomous AI refers to systems that can operate independently, making decisions and taking actions without continuous human intervention.

Autonomous AI agents are often used in complex environments where real-time decision-making and adaptability are required.

Computer vision

Computer vision is a field of AI that enables machines to interpret and understand visual data such as images and videos.

Computer vision applications include object detection, facial recognition, and quality inspection across industries.

Context graph

A context graph is a structured representation of relationships between data, entities, and interactions used by AI systems to maintain context.

In AI, a context graph helps agents understand dependencies, history, and connections, improving decision-making and relevance.

Deep learning

Deep learning is a subset of machine learning that uses neural networks with multiple layers to process complex data.

Deep learning models are commonly used for tasks such as image recognition, speech processing, and natural language understanding.

Digital worker

A digital worker is an AI-powered entity that performs tasks traditionally done by humans.

An AI digital worker can automate repetitive processes, support operations, and work alongside human teams within a digital worker ecosystem.

Edge AI

Edge AI refers to running AI models directly on devices or near the data source rather than in centralized cloud environments.

An edge AI platform enables real-time processing, reduced latency, and improved data privacy.

Generative AI

GenAI systems use large language models and other techniques to generate outputs based on patterns learned from data.

Generative AI is a type of artificial intelligence that creates new content such as text, images, code, or audio.

Hallucinations

AI hallucinations occur when an AI system generates incorrect, misleading, or fabricated information that appears plausible.

Understanding what AI hallucinations are is critical for ensuring reliability, especially in enterprise and decision-critical applications.

Intelligent automation

Intelligent automation combines AI with automation technologies to execute tasks, workflows, and processes with minimal human intervention.

Intelligent automation tools enable organizations to streamline operations and improve efficiency at scale.

Intelligent document processing

Intelligent document processing is the use of AI to extract, classify, and process data from documents.

Intelligent document processing software helps automate workflows involving invoices, forms, and contracts, improving accuracy and speed.

Large language models

Large language models (LLMs) are AI models trained on vast amounts of text data to understand and generate human language.

Large language models power applications such as chatbots, copilots, and generative AI systems.

Machine learning

Machine learning (ML) is a subset of AI that enables systems to learn from data and improve performance over time without explicit programming.

ML models are widely used for prediction, classification, and pattern recognition across industries.

Mentor

Mentor is an OutSystems AI capability that supports agentic development by assisting with application generation and development workflows.

It helps teams accelerate development by translating inputs into working applications and components within a governed environment.

Model deployment

Model deployment is the process of making an AI model available for use in real-world applications.

AI model deployment involves integrating models into systems, ensuring scalability, and monitoring performance in production environments.

Model training

Model training is the process of teaching an AI model to recognize patterns by exposing it to data.

AI model training involves adjusting parameters to improve accuracy and performance for specific tasks.

Multi-agent systems

Multi-agent systems are environments where multiple AI agents interact and collaborate to complete tasks.

Multi-agent AI systems enable complex problem-solving by distributing responsibilities across agents.

Multimodal AI

Multimodal AI refers to AI systems that can process and understand multiple types of data, such as text, images, and audio.

Multimodal AI agents can combine inputs to generate richer and more accurate outputs.

Natural language processing

Natural language processing (NLP) is a field of AI that enables machines to understand, interpret, and generate human language.

Natural language processing in AI powers applications such as chatbots, translation, and sentiment analysis.

Neural networks

Neural networks are computational models inspired by the human brain that are used to recognize patterns in data.

Artificial neural networks form the foundation of deep learning and are used in tasks such as vision and language processing.

Orchestration

Orchestration is the coordination of multiple systems, processes, or AI agents to execute complex workflows.

AI agent orchestration ensures tasks are completed efficiently, dependencies are managed, and workflows remain aligned with business logic.

Token

A token in AI is a unit of text, such as a word or part of a word, used by models to process language.

Understanding what a token is in AI is important for managing model inputs, outputs, and usage costs.

Vibe coding

Vibe coding is an informal term describing the use of AI tools to generate code quickly based on prompts or intent rather than detailed specifications.

Vibe coding AI reflects a shift toward faster, more intuitive development workflows, though it often requires validation and refinement.

Workflow automation

Workflow automation is the use of technology to execute processes and tasks without manual intervention.

AI workflow automation enhances this by incorporating decision-making, enabling AI agents to automate complex workflows across systems.