agents

A software entity that perceives its environment, reasons about what actions to take, executes those actions (often via tools), and observes the results in a loop until achieving a goal or being ter...

Also: AI Agent, Intelligent Agent, LLM Agent

The iterative cycle an agent follows: perceive the current state, reason about what to do, execute an action, observe the result, and repeat until the goal is achieved or a termination condition is me...

Also: Reasoning Loop, Action Loop, Observe-Think-Act Loop

Mechanisms that allow an agent to retain and access information beyond the current context window. Memory enables agents to learn from past interactions, maintain state across sessions, and reference ...

Also: Memory System, Agent State Persistence

The coordination of multiple agents or agent components to accomplish complex tasks. Orchestration determines which agent handles which subtask, manages communication between agents, handles failures ...

Also: Agent Coordination, Agent Management

The information an agent maintains and updates during execution to track progress, store intermediate results, and inform decisions. State includes: current goal, completed steps, pending actions, acc...

Also: State Management, Agent Context

A software system that exhibits agent-like behavior—perceiving, reasoning, and acting—but may not fit the strict definition of a single coherent agent. Agentic systems often combine multiple compone...

Also: Agentic Application, Agentic AI, Agent System

An agent that operates with minimal or no human intervention during execution. Autonomous agents make decisions, take actions, and handle errors independently, only surfacing to humans for high-stakes...

Also: Fully Autonomous Agent, Self-Directed Agent

An agent that can write and execute code as part of its problem-solving process. Unlike agents that merely generate code for humans to run, code- executing agents have access to a runtime environment ...

Also: Code Agent, Code Interpreter Agent, Programming Agent

A system design pattern where human judgment is required at defined points in an automated process. In agent systems, human-in-the-loop typically means: (1) approval before high-stakes actions, (2) re...

Also: HITL, Human Oversight, Human Review

A pattern for running AI coding agents autonomously by wrapping them in an external loop that restarts execution after each completion or failure until a verifiable completion condition is met. Unli...

Also: Ralph Wiggum Loop, Ralph Loop, Persistence Loop, Autonomous Iteration

A system composed of multiple agents that interact, collaborate, or compete to achieve individual or collective goals. Agents in a multi-agent system may be homogeneous (same capabilities) or heteroge...

Also: MAS, Multi-Agent Architecture, Agent Swarm

The process by which an agent formulates a sequence of steps or strategy to achieve a goal before executing actions. Planning separates "what to do" from "doing it," allowing the agent to reason about...

Also: Task Planning, Agent Planning, Plan Generation

The process by which an agent (or LLM) derives conclusions, makes decisions, or solves problems through intermediate steps rather than direct pattern matching. In LLM contexts, reasoning typically man...

Also: LLM Reasoning, Chain-of-Thought, Deliberation

The process by which an agent evaluates its own outputs, reasoning, or behavior and uses that evaluation to improve. Reflection enables self- correction without external feedback—the agent acts as its...

Also: Self-Reflection, Self-Critique, Meta-Cognition

An agent whose primary role is to coordinate, delegate to, and oversee other agents rather than perform tasks directly. The supervisor receives high-level goals, decomposes them into subtasks, assigns...

Also: Orchestrator Agent, Manager Agent, Meta-Agent

An agent that extends its capabilities by invoking external tools—APIs, functions, code interpreters, or other services. The agent decides when to use which tool based on the task, formulates appropri...

Also: Tool Agent, Function-Calling Agent

A predefined sequence or graph of steps that executes in a determined order, where the path through the workflow is decided at design time, not runtime. Workflows may have conditional branches, but th...

Also: Pipeline, Flow, DAG, Directed Acyclic Graph