Research Agent

Agentic AI

AI systems that can autonomously plan, reason, and take actions to achieve goals with minimal human intervention.

AI Agent

An autonomous software entity that perceives its environment, makes decisions, and takes actions to achieve specified objectives.

Autonomous Agent

An AI agent capable of operating independently, making decisions and taking actions without continuous human oversight.

Reactive Agent

An AI agent that responds to environmental stimuli with predefined actions without maintaining an internal model of the world.

Deliberative Agent

An AI agent that maintains an internal model of its world and reasons about actions before executing them.

BDI Architecture

Belief-Desire-Intention — an agent architecture where agents reason about beliefs, desires, and intentions to decide actions.

Agent Planning

The ability of an AI agent to formulate a sequence of actions to achieve a goal from its current state.

Tool Use

The capability of AI agents to interact with external tools, APIs, and services to extend their functionality.

Agent Hierarchy

An organisational structure where agents are arranged in levels, with higher-level agents delegating tasks to lower-level ones.

Supervisor Agent

An agent that oversees and coordinates the work of other agents, making high-level decisions and resolving conflicts.

Agent Sandbox

An isolated environment where AI agents can safely execute actions and experiment without affecting production systems.

Human-on-the-Loop

A system where humans monitor AI operations and can intervene when necessary, but don't approve every action.

A large collection of AI agents operating collaboratively using emergent behaviour patterns to solve complex tasks.

Safety constraints imposed on AI agents that limit their action space, prevent dangerous operations, enforce budgets, and require approval for irreversible decisions.

Reasoning and Acting — a framework where language model agents alternate between reasoning traces and action execution.

Safety constraints and boundaries that limit agent behaviour to prevent harmful, unintended, or out-of-scope actions.

A system design where human oversight and approval are required at critical decision points in automated processes.

A workflow pattern where multiple specialised agents are sequentially connected, with each agent's output feeding the next.

A system composed of multiple interacting AI agents that collaborate, negotiate, or compete to solve complex problems.

The accumulated information, history, and environmental state that informs an AI agent's decision-making.