Most Augmented Cognition systems use physiological measures to detect critical cognitive states and trigger adaptation strategies to address the problem state and restore or augment performance. Without accounting for context, however, it is likely that adaptations are triggered or withdrawn at inopportune moments, potentially disrupting or confusing the user. We have developed an approach to dynamic adaptation management that processes task and operator state indicators to dynamically select and configure context-sensitive adaptation strategies in real time. This dynamic approach is expected to avoid much of the potential cognitive cost associated with adaptations. We provide an overview of our conceptual approach, describe a proof-of-concept implementation, and summarize user feedback and initial lessons-learned from a small survey.