Software removal candidate evaluation AI agent

  • Release version: Australia
  • Updated August 14, 2026
  • 2 minutes to read

    • This Software Asset Management agent identifies unused or underused software licenses and initiates reclamation after user confirmation.

    Workflow

    1. Identify the target product. If a Product ID is provided, use it directly. Otherwise, present available products for the user to select, optionally filtered by Publisher ID.
    2. Fetch removal candidate analysis data for the selected product. If no data is found, inform the user and end.
    3. Validate that the data supports reclamation. The checks differ based on software type (installed vs. subscription) but follow the same pattern: confirm recent usage or activity data exists, and confirm the ratio of removal candidates to total installations or subscriptions is within an acceptable range. If any check fails, inform the user with a specific reason and end.
    4. Present the number of eligible removal candidates and ask the user to confirm reclamation. Only non-VIP users with notifications enabled are included.
    5. Run the reclamation workflow and report the result. If successful and there are candidates stuck in "Awaiting Revocation" status for 60 days, flag them for review.
    Table 1. Configuration
    Field Description
    Allow third party to access this AI agent

    When enabled, third-party AI agents can use this agent. This value is off (false) by default. This setting is defined in the AI Agent configs [sn_aia_agent_config] table on the External discoverable field.
    Allow AI specialists to access this AI agent

    When enabled, AI specialists can use this agent. This value is off (false) by default. When set to true, more configuration options for tools become available so that an AI specialist can map inputs and response templates to tool outputs. This setting is defined in the AI Agent configs [sn_aia_agent_config] table on the Specialist enabled field.
    Manage long-term memory

    When enabled, all previous user interactions are used as context for the LLM. This value is off (false) by default. This setting is defined by the sn_aia.ltm.enable_long_term_memory system property. For more information, see ServiceNow Otto AI agents reference.
    Tools
    Scripts
    Find activity job status of the product
    Find removal candidates analysis
    Reclaim removal candidates
    Conversational topic
    Get products for removal candidate
    Agent roles (ACLs) sam_user
    Data access roles sam_user
    Triggers

    Optional. None defined by default. An admin can specify triggers if desired. For more information, see Add a trigger to an AI agent.
    Channels

    Configure an assistant for Virtual Agent or ServiceNow Otto panel using Assistant Designer.
    Used in agentic workflows

    Evaluate software removal candidate Agentic workflow

    Learn more about Software Asset Management at Software Asset Management.