Skip to main content
COMPEL Body of Knowledge
Get Certified Platform

COMPEL Glossary / orchestration-plane

Orchestration plane

The layer of an AI system that coordinates prompts, retrievals, tool calls, safety filters, and routing between the user and one or more models.

What this means in practice

Distinct from the model plane because orchestration logic is the locus of most governance controls — policy enforcement, audit logging, and human-in-the-loop gates all live here.

Synonyms

orchestration layer , AI orchestration plane

Related Terms Network

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

Related terms for Orchestration plane Network graph showing 4 related glossary terms connected to Orchestration plane. Orchestration … AI referen… Knowledge … Agent loop Policy eng…
4 related concepts connected to Orchestration plane.

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
  • AI reference architecture — A canonical layered model — client, orchestration, model, knowledge, observability planes — that every AI system maps onto.
  • Knowledge plane — The layer of an AI system that stores and serves non-parametric knowledge to the model — through retrieval over vector stores, traditional indexes, and tool-based data access.
  • 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.
  • Policy engine — A declarative rule engine that gates agent actions — via ABAC-style policies evaluating identity, resource, environment, and action attributes.

See also

  • AI reference architecture — A canonical layered model — client, orchestration, model, knowledge, observability planes — that every AI system maps onto.
  • Knowledge plane — The layer of an AI system that stores and serves non-parametric knowledge to the model — through retrieval over vector stores, traditional indexes, and tool-based data access.
  • 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.
  • Policy engine — A declarative rule engine that gates agent actions — via ABAC-style policies evaluating identity, resource, environment, and action attributes.