--- sourceDocument: Australia Enable AI sourceDocumentLink: https://www.servicenow.com/docs/r/australia/intelligent-experiences Release : - australia ft:locale : - en-US ft:publication_title : - Australia Enable AI ft:clusterId : - platai bundleId : - platai workflow : - Platform --- # Long-term memory categories for Now Assist AI Agents # Long-term memory categories {#ariaid-title1} Release version: Australia Updated March 18, 2026 ![](https://www.servicenow.com/docs/portal-asset/ico-clock) 2 minutes to read Summarize ![AI sparkle icon](https://servicenow.com/docs/portal-asset/ai-sparkle-icon) Summarized using AI This content was generated using new OpenAI-powered functionality. Results are provided on an as is basis and are not guaranteed to be accurate or complete. ## Summary of Long-term memory categories Long-term memory (LTM) categories enable Now Assist AI agents to learn, retain, and personalize responses based on semantic information about users over time. These categories define distinct types of user-specific facts---such as software preferences or workplace context---that the agent stores and retrieves to enhance interaction without requiring repeated context from the user. Show full answer Show less ## How LTM Categories Work When an AI agent interacts with a user, the platform evaluates the conversation for facts matching the agent's mapped LTM categories. Matching facts are stored as semantic memory records in the **AI Agent Memories** table, scoped by user and category. On future interactions, the agent accesses these memories to tailor responses accordingly. LTM categories are globally defined and must be explicitly mapped to agents to control what information they retain and use. ## Default and Custom Categories The platform provides default LTM categories including: * **Software and tools:** User software applications and configurations. * **Work context:** User role, department, location, and workplace preferences. * **User preferences:** Communication style, language, and notification settings. Organizations can create custom categories to better fit their specific use cases and tailor agent learning accordingly. ## Memory Extraction and Storage During memory extraction, a large language model (LLM) prompt assesses interaction content against category descriptions. Matching information is saved as semantic memory records with fields for category, user, and fact (stored as JSON). These memories are retrieved at runtime using retrieval-augmented generation (RAG) to personalize agent responses dynamically. ## Practical Considerations for ServiceNow Customers * Use clear, specific category descriptions to improve extraction accuracy and reduce errors. * Map only relevant categories to each agent to optimize performance and avoid unnecessary processing delays. * To verify memory extraction, review the AI Agent Memories table filtered by **Type = Semantic** and relevant user or agent identifiers. By effectively configuring LTM categories, ServiceNow customers can enhance AI agent personalization, leading to more context-aware and efficient user interactions. Long-term memory (LTM) categories define the types of semantic information that a Now Assist AI agent can learn and retain about users over time. You can add new categories and map them to specific agents to personalize agent responses based on accumulated user context. Semantic memory in the AI agent Memories table (`sn_aia_memory_list`) is organized by LTM categories. Each category represents a distinct type of user-specific information, such as software preferences, workplace context, or communication style. By mapping categories to an agent, you control what the agent learns and retains across interactions. ## How LTM categories work {#aia-ltm-categories-new__section_ltm_overview} When an agent executes, the platform evaluates the interaction for user-specific facts that match the agent's configured LTM categories. Matched facts are stored as semantic memory records in the AI Agent Memories \[sn_aia_memory\] table, scoped to the user and category. On subsequent interactions, the agent retrieves relevant semantic memories and uses them to personalize its responses without requiring the user to repeat context. LTM categories are defined globally and can be mapped to one or more agents. An agent only learns and retrieves memories for the categories explicitly mapped to it. ## Default LTM categories {#aia-ltm-categories-new__section_default_categories} The platform includes the following default LTM categories: Software and tools : Captures information about applications, tools, and software configurations relevant to the user, such as operating system version or approved applications. Work context : Captures facts about the user's role, department, location, and workplace preferences, such as remote work setup or team structure. User preferences : Captures communication preferences and interaction style, such as preferred language, response format, or notification settings. You can extend this list by creating custom categories suited to your organization's use cases. ## How categories affect memory extraction {#aia-ltm-categories-new__section_extraction_behavior} During memory extraction, the platform runs an LLM prompt that evaluates the agent interaction against the descriptions of each mapped LTM category. If the interaction contains information that matches a category, a semantic memory record is created or updated in the AI Agent Memories table with the following fields: Category : The LTM category that the memory is associated with. User : The user whose interaction generated the memory. Memory : The extracted user-specific fact, stored as a JSON object. Type : Set to Semantic for category-based memories. Semantic memories are retrieved at runtime using retrieval-augmented generation (RAG) and injected into the agent prompt to personalize the response for the current user. ## Considerations {#aia-ltm-categories-new__section_considerations} * Category descriptions directly influence LLM extraction quality. Use specific, unambiguous language to reduce false positives or missed extractions. * Mapping too many categories to a single agent can increase extraction processing time. Map only the categories relevant to the agent's use case. * To verify that semantic memories are being extracted, open the AI Agent Memories table and filter by Type = Semantic and the relevant agent or user. {#aia-ltm-categories-new__ul_css_243_q3c}