DEX diagnosis AI agent

This AI agent specializes in structured root cause diagnosis of device and application performance issues through a step-by-step process. This agent aggregates device health metrics, event logs and historical incident data, then systematically evaluates each source to isolate relevant evidence.

Workflow

The agent does not perform remediation, but it supports IT support and operations teams by providing a high-confidence diagnosis, highlighting affected components, key data sources, and patterns—ensuring clarity and traceability in issue investigation.

1. Use the Device diagnostic data collector tool to gather issue details, device specifications (OS, version, RAM, CPU, disk space), health metrics (all available categories), and device events (system and service events).

2. Use the Similar incidents retriever tool to find past incidents with related symptoms, affected devices, components, or resolution patterns.

3. Call the Zoom call diagnosis skill ONLY when the issue explicitly indicates Zoom application.

4. Review the collected data and keep only the sources that provide useful information.

5. From the remaining data, identify the most probable root cause with supporting evidence.

6. Present the diagnosis in a bulleted list and include the following: incident number (if available), device information (OS, version, model), root cause with explanation, supporting evidence (metrics, events, patterns), and the confidence level with justification. Use clear headers and structured sections for readability.

7. Display the diagnosis to the user before proceeding.

<table><thead><tr><th>

Field

</th><th>

Description

</th></tr></thead><tbody><tr><td>

Allow third party to access this AI agent

</td><td>

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.

</td></tr><tr><td>

Allow AI specialists to access this AI agent

</td><td>

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.

</td></tr><tr><td>

Manage long-term memory

</td><td>

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.

</td></tr><tr><td>

Tools

</td><td>

• Scripts

Device diagnostic data collector

Similar incidents retriever

• Generative AI skill

Zoom Call Diagnosis Data Collector

</td></tr><tr><td>

Allowed user roles The specific user roles that can access this AI agent.

</td><td>

sn_incident_write

</td></tr><tr><td>

Data access roles The specific user identity roles that determine which data the AI agent can access and what actions it can take.

</td><td>

dex.incident.ai.worker

access_analyzer_ai_user, action_designer, action_write_enabled, actsub_user, agent_client_collector_user, agent_role_config_viewer, agent_workspace_user, app_service_user, canvas_user, certification, cmdb_ms_user, cmdb_query_builder, cmdb_query_builder_read, cmdb_read, contact_user, data_manager_user, data_mapping_user, decision_table_admin, decision_table_reader, dependency_views, email_client_template_read, email_composer, fd_read_actions, fd_read_operations, fd_read_operations_all, flow_designer, flow_operator, flow_write_enabled, interaction_agent, itil, knowledge, mbplus_reader, notify_view, now_assist_panel_user, one_extend_viewer, openapi_admin, pa_viewer, personalize_decision_table_input, platform_ml_di.admin, platform_ml_read, prompt_library_user, report_user, role_viewer, sam_user, scan_user, service_status_subscriber, snc_platform_rest_api_access, sn_ace.ace_user, sn_aia.viewer, sn_ai_filter_assist.user, sn_ai_filter_tracker.user, sn_bm_client.benchmark_data_viewer, sn_change_read, sn_change_write, sn_cimaf.sn_cimaf_read, sn_cmdb_user, sn_comm_management.comm_plan_viewer, sn_conv_fa.conv_fa_designer, sn_data_kit.analyst, sn_dex.ai_user, sn_dex.engineer, sn_dex.service_desk_user, sn_dex.user, sn_dex_content.user, sn_dex_desktop.notification_template_admin, sn_dex_ms365.user, sn_dex_score.dashboard_user, sn_dex_zoom.user, sn_diagram_builder.db_read, sn_gaf.data_viewer, sn_gaf.data_writer, sn_gd_guidance.guidance_user, sn_incident_read, sn_incident_write, sn_itam_recomm.recommendations_read, sn_itsm_aia.sn_aia_chg_conflict, sn_itsm_aia.sn_aia_chg_quality, sn_itsm_aia.sn_aia_chg_schedule, sn_itsm_contact_query, sn_mcp_client.viewer, sn_nb_action.next_best_action_user, sn_nowassist_admin.user, sn_now_canvas_ai.interactive_view_user, sn_pren.experience_issue_read, sn_problem_read, sn_problem_write, sn_prompt_assist.prompt_developer, sn_publications_recipients_list_user, sn_publications_recipients_user, sn_query_gen.user, sn_reacf.sn_remedial_action_read, sn_request_approver_read, sn_request_read, sn_request_write, sn_skill_builder.viewer, sn_sla_definition_query, sn_sow.it_agent_dashboard_user, sn_sow.sow_home, sn_sow.sow_list, sn_sow.sow_user, sn_sttrm_condition_read, sn_sub_man.admin, sn_udc.basic_read, sn_uib_collab.user, sn_uxc_gen_ai.sn_aia_sla_explain, sn_workflow_studio.workflow_studio_read, survey_reader, task_editor, template_editor, template_read_global, tracked_file_reader, trigger_designer, trigger_designer_read, usage_admin, view_changer, viz_creator, workflow_ai_author, workspace_user

</td></tr><tr><td>

Triggers

</td><td>

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

</td></tr><tr><td>

Channels

</td><td>

Enable the AI agent for the ServiceNow Otto panel.

</td></tr><tr><td>

Used in agentic workflows

</td><td>

DEX issue diagnosis and resolution workflow

</td></tr></tbody> </table>Learn more about IT Service Management at IT Service Management.

Parent Topic:IT Service Management AI agents