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 / offline-evaluation
Offline evaluation
Assessment of an AI system against static datasets — training hold-out, validation set, benchmark corpus — without exposure to live user traffic.
What this means in practice
Required before any online rollout because offline experimentation catches catastrophic regressions cheaply, but offline-only signals do not reliably predict online behavior.
Synonyms
offline test , batch evaluation , held-out evaluation
See also
- Online evaluation — Assessment of an AI system under live traffic using randomized or sequential experimental designs — A/B test, multi-armed bandit, canary, or interleaving.
- Data leakage — Information from the test or validation set inadvertently entering training — through preprocessing, feature engineering, target encoding, or time-ordered splits — inflating offline metrics and producing over-optimistic ship decisions.
- AI experiment — A structured comparison producing evidence for a decision — about a model version, a prompt, a feature set, a retrieval strategy, or a deployment change.