Troubleshooting steps identification AI agent

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

    • An AI agent responsible for gathering required context, identifying troubleshooting steps by comparing with KBs, similar cases and standard operating manuals, and proposing additional troubleshooting steps.

    Workflow

    The agent helps users complete tasks related to troubleshooting steps identification.
    1. Retrieve case details and identify troubleshooting actions already attempted by the user to avoid duplication.
    2. Search for relevant troubleshooting guidance from similar cases and knowledge articles using the case description. If no relevant results are found, exit with the predefined message.
    3. Analyze retrieved cases and knowledge articles to extract actionable troubleshooting steps with correct source attribution.
    4. Identify and process any related documents linked to the search results, applying deterministic document selection logic and extracting troubleshooting steps when documents exist.
    5. Combine troubleshooting steps from cases, knowledge articles, and documents, then remove steps already attempted by the user or semantically equivalent duplicates.
    6. Present only unique, value-added troubleshooting recommendations in a structured format, clearly separating top recommendations, additional suggestions, and a fully hyperlinked sources section.
    7. Ask for confirmation before updating work notes, update them only upon approval, display the exact confirmation message when successful, and then exit the workflow.
    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
    Script
    Get case details using number and fields
    Get document list using comma separated list of 'Id' values
    Update the work notes of the case
    Subflows
    Get case details using number and fields
    Submit and Fetch Results
    Search retrieval
    Get relevant knowledge articles
    Get Similar Cases
    Agent roles (ACLs) sn_esm_agent
    Data access roles sn_customerservice_agent, sn_customerservice.consumer_agent, platform_ml_di.creation_agent
    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

    Not applicable.

    Learn more about Customer Service Management at Customer Service Management.