Skip to main content
COMPEL Body of Knowledge
Get Certified Platform

COMPEL Glossary / agentic-ai-system

Agentic AI system

An AI system that executes tools, loops over multi-step plans, maintains state across steps, and pursues goals semi-autonomously.

What this means in practice

Distinct from a conversational AI system because the agentic system takes actions with real-world side effects; its governance surface spans tool scope, state boundary, and human-intervention protocol.

Synonyms

agentic system , agent-based AI system

Related Terms Network

This diagram shows how Agentic AI system connects to other concepts in the COMPEL body of knowledge. Each linked node is a term you can explore in turn.

Related terms for Agentic AI system Network graph showing 4 related glossary terms connected to Agentic AI system. Agentic AI sys… Agent runt… Agent taxo… Agent loop Excessive …
4 related concepts connected to Agentic AI system.

The COMPEL Glossary Graph visualizes relationships between framework terminology, showing how concepts interconnect across domains, stages, and pillars. Term nodes cluster by pillar affiliation while cross-references reveal semantic dependencies — for example, how risk appetite connects to control effectiveness, model governance, and assurance requirements. This network representation helps practitioners navigate the framework vocabulary and understand that COMPEL terminology forms a coherent conceptual system rather than isolated definitions.

Accessible list of related terms
  • Agent runtime — The execution substrate that hosts the agent loop, its tool calls, state, and recovery logic — e.g., LangGraph, CrewAI, AutoGen, or OpenAI Agents SDK.
  • Agent taxonomy — A seven-category classification — conversational, task, workflow, RPA-adjacent, research, code, embodied — used to scope an agent's design, risk profile, and governance controls.
  • Agent loop — The iterative pattern in which a model plans, calls tools, observes the results, and replans — continuing until a goal is met, an iteration budget is exhausted, or a human intervenes.
  • Excessive agency — A failure mode in which an LLM has been wired into tools and permissions whose blast radius exceeds what its supervision and validation logic can safely bound.

See also

  • Agent runtime — The execution substrate that hosts the agent loop, its tool calls, state, and recovery logic — e.g., LangGraph, CrewAI, AutoGen, or OpenAI Agents SDK.
  • Agent taxonomy — A seven-category classification — conversational, task, workflow, RPA-adjacent, research, code, embodied — used to scope an agent's design, risk profile, and governance controls.
  • Agent loop — The iterative pattern in which a model plans, calls tools, observes the results, and replans — continuing until a goal is met, an iteration budget is exhausted, or a human intervenes.
  • Excessive agency — A failure mode in which an LLM has been wired into tools and permissions whose blast radius exceeds what its supervision and validation logic can safely bound.

Related articles in the Body of Knowledge