Skip to main content

COMPEL Glossary / agent-taxonomy

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.

What this means in practice

Different categories have different failure modes, different regulatory exposure, and different typical lifecycles.

Synonyms

agent classification , agent-type taxonomy

See also

  • Agentic AI system — An AI system that executes tools, loops over multi-step plans, maintains state across steps, and pursues goals semi-autonomously.
  • Agent autonomy spectrum — The continuum along which agentic AI systems operate — from single-turn assistance through tool-augmented reasoning to fully autonomous multi-step execution — typically described with named gradations (Level 0 through Level 5).

Related articles in the Body of Knowledge