Memory · Data store
User Preference Profile Store
Data storeMemoryCognition & Memoryarc:UserPreferenceProfileStore
A persistent per-user store of stable preferences learned across many interactions, such as communication style, preferred modalities, recurring constraints, preferred time slots and priorities.
Responsibility. Persists learned per-user preferences for personalization across sessions.
Also known as: Persistent preferences, User model, Long-term context
Relationships
is read by dependency
is written by dependency
has access controlled by control
Design guidance
- SHOULD restrict use of learned behavioural insights to the context they were consented for (e.g., scheduling), prohibiting surveillance or employee monitoring use.
Quantitative guidance
As stated by the sources; verify before use.
- Over 100+ interactions, generic population-level models progressively specialize toward individual preferences (Ch10.2).
Classification
- Patterns
- Hierarchical long-term memoryCross-session personalization
- Quality attributes
- Interaction capability (ISO/IEC 25010)
- Risks mitigated
- Users repeatedly restating preferencesStateless forgetting
Sources
- Ch10.2: T. Nguyen, "Proactive Agents," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 10.2. ISBN: 9798244538229.