Skip to main content
COMPEL Body of Knowledge
Get Certified Platform

COMPEL Glossary / agent-trace

Agent trace

A span hierarchy that captures a multi-step agent execution — loop iterations, tool calls, memory reads and writes — with enough fidelity to reconstruct the agent's full decision path.

What this means in practice

Required artefact for post-incident review and EU AI Act Article 12 record-keeping; typically stored alongside the underlying AI trace.

Synonyms

agentic trace , multi-step agent trace

Related Terms Network

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

Related terms for Agent trace Network graph showing 4 related glossary terms connected to Agent trace. Agent trace AI trace Agent obse… Replayabil… Observabil…
4 related concepts connected to Agent trace.

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 trace — A span hierarchy — client → orchestration → retrieval → model → tool — capturing a single AI request end-to-end, including prompts, responses, tool calls, and token usage.
  • Agent observability — The logging, tracing, and evaluation infrastructure that makes an agent's plans, tool calls, memory reads/writes, and decisions auditable after the fact.
  • Replayability — The ability to deterministically reproduce an agent trace given captured inputs — a recorded session, the prompt, the tool responses, the random seed.
  • Observability for AI — The set of telemetry — prompt/response capture, retrieval traces, tool-call records, token-cost metrics, and evaluation signals — that makes an AI system operable and auditable.

See also

  • AI trace — A span hierarchy — client → orchestration → retrieval → model → tool — capturing a single AI request end-to-end, including prompts, responses, tool calls, and token usage.
  • Agent observability — The logging, tracing, and evaluation infrastructure that makes an agent's plans, tool calls, memory reads/writes, and decisions auditable after the fact.
  • Replayability — The ability to deterministically reproduce an agent trace given captured inputs — a recorded session, the prompt, the tool responses, the random seed.
  • Observability for AI — The set of telemetry — prompt/response capture, retrieval traces, tool-call records, token-cost metrics, and evaluation signals — that makes an AI system operable and auditable.