Use agentic workflows - Product Documentation: Zurich

Use agentic workflows

Using agentic workflows in ServiceNow Otto for Telecommunications, Media, and Technology (TMT)

Use the ServiceNow Otto for TMT agentic workflows to complete tasks autonomously.

Table 1. Available agentic workflows for ServiceNow Otto for TMT AI agent collection Agentic workflow name Description Available AI agents Test and repair telecom service issues The agentic workflow gets triggered when the service problem case is assigned to the case agent and the state of the case is Open or New. The customer raises a case on the service disruption.

The service problem case (SPC) starts with the SPC number.

This AI agent handles service problem case requests that require troubleshooting, diagnostics, analysis, or resolution when given a task identifier or description. It’s also retrieves relevant context and details related to the task.

AI agents perform their tasks to resolve the customer issue.

Service problem manager AI agent Customer payment status AI agent Preliminary troubleshooter AI agent On-demand service tester AI agent Service repairer AI agent

Help remediate bill issues The agentic workflow handles billing inquiry requests by analyzing current invoice usage. It provides insights into high bill usage and suggests alternative plans based on customer usage patterns. For example, if a customer with a domestic mobile connection uses it internationally, they may incur extra charges. The bill analysis can identify such international usage and provide an optimal plan to help manage costs. Billing account information collector AI agent Recommended plans AI agent Billing invoice data collector AI agent

Analyze network incidents Assists customer agents in resolving a given incident. It helps customer agents to resolve network tickets by tracking it and creating an actionable task. Network ticket resolution AI agent Ticket readiness AI agent Network correlation monitor AI agent Network ticket actionable steps generation AI agent Network remediation generation AI agent

Analyze risks and recommend solutions Retrieves applicable risks and proactively suggests solutions with minimal user intervention. Success risk manager AI agent Monitor engagement health Monitors the health score trends for all active engagements and triggers risk signals when declined. Success trend AI agent Success health monitor AI agent

Support renewals and expansion Assesses engagements due for renewal, analyzes trends, and recommends renewal strategies. Renewal analysis AI agent Value realization assessor AI agent Success insight AI agent

Trigger risk mitigation touchpoint Automates the creating and scheduling of meetings for a specific user. Meeting draft creator AI agent Draft meeting scheduler AI agent

Service Exchange onboarding Assists the provider with the consumer registration process, including step-by-step guidance, error checks during registration, and support for resolving any errors. Registration Initiator AI agent Registration Error Monitor AI agent

Customer voice quality issue resolution Assists customer service representatives in resolving customer voice quality issues. Ticket creation AI agent Customer interaction context gatherer AI agent RADCOM ticket handling agent customer profile (External agent)

Enable security implementation to execute AI agents and agentic workflows through access control lists (ACLs) and user identities. ACLs provide the Run As capability to let agents and agentic workflows execute actions either as a dynamic user or as an AI user. For more information, see Implement access control in AI agents .

Important: By default, all agentic workflows and AI agent records are read only. To run the AI agents autonomously, you must first duplicate the agentic workflow, and then proceed with the following steps:

Activate the agentic workflow. Activate all agents within the agentic workflow. Activate the trigger to invoke the agentic workflow automatically. If you prefer to invoke it manually, activating the trigger isn’t necessary.

Once you duplicate the agentic workflow, adjust the settings according to your requirements. Next, you activate the duplicated agentic workflow. You can also test the agentic workflow to analyze its performance in the AI Agent Studio , while it executes the instructions that you defined.

There might be AI agents installed on your instance that are not used in agentic workflows. To learn how to see all agents that are available to you, see Find AI agents .