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.
COMPEL Glossary / agent-observability
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.
What this means in practice
Governance artefact — not an engineering nicety — because without observability an organization cannot evidence compliance with NIST AI RMF MEASURE/MANAGE or reconstruct an agentic incident for regulators.
Synonyms
agent tracing , agent telemetry , agentic audit trail
See also
- Agent memory — The stored context, preferences, observations, and state an agent accumulates across turns or sessions.
- Evaluation harness — The infrastructure that runs capability, regression, safety, and human-review evaluations on an LLM feature on a defined cadence.