L1 IT Service Desk AI Specialist FAQ

Christopher Ell · 2 hours ago

FAQ: L1 IT Service Desk AI Specialist

Last revised October 20, 2026

Contents: Definitions · About the Specialist · Enablement · Solution Questions

Definitions

1. What is the official name?

The name of the solution is the L1 IT Service Desk AI Specialist.
Zero Touch Support is an “Outcome” that customers can achieve by leveraging ITSM and its Agentic capabilities. The three pillars of Zero Touch Support are Omnichannel Self-Service, Accelerated Resolution, and Proactive Deflection. Under each pillar are different solutions that support it. The L1 IT Service Desk AI Specialist is under Accelerated Resolution.
The name of the plugin is ZTSD, or Zero Touch Service Desk.

2. AI Specialist

In the ServiceNow context, an AI Specialist, such as the Level 1 IT Service Desk AI Specialist, is a digital coworker that encapsulates a full role and automates a range of related tasks end-to-end within that role. For example, the L1 IT Service Desk AI Specialist can self-assign tickets, diagnose issues, apply fixes, escalate when needed, and document all actions, operating autonomously within existing workflows and assignment groups.
An AI agent, by contrast, typically refers to a more narrowly focused automation that handles a single task or a limited set of actions, such as resetting a password or answering a specific question. AI agents are often invoked for point solutions, while AI Specialists are designed to manage the entire lifecycle of work for a defined role, integrating multiple tasks, decision points, and AI agents.
In summary, AI Specialists are role-based, multi-tasking digital coworkers that operate autonomously across a workflow, whereas AI agents are single-task automations or assistants. The AI Specialist for a Level 1 Service Desk role is an example of this broader, role-based automation in ServiceNow.

3. Digital Worker

This is an obsolete term with the same meaning as “AI Specialist.”

4. Autonomous Workforce

An autonomous workforce is a collection of AI Specialists, each specializing in a different domain.

5. Level 1 IT Service Desk AI Specialist (L1ITSDAIS)

This is ServiceNow’s first Autonomous Worker, now available to select customers. Other Autonomous Workers are on the backlog to fill out the larger Autonomous Workforce.

About the Specialist

6. Why are we announcing Autonomous Workforce?

Enterprises are drowning in routine work. Password resets, benefits questions, and order status checks pile up faster than teams can hire. AI agents helped, but they’re too technical and task-specific for front-line managers who think in roles, not individual tasks. ServiceNow Autonomous Workforce introduces AI Specialists that don’t just complete tasks. They hold entire job functions and resolve work end-to-end. Built on 20 years of enterprise workflow intelligence, they onboard in clicks, scale infinitely, and continuously improve. We’re announcing this because it represents a paradigm shift: from AI as a tool to AI as a teammate.

7. Where does Zero Touch Support fit relative to Autonomous IT, etc.?

We see Autonomous IT as a path to zero: zero service outages, zero security breaches, and zero-touch operations, whether that’s for your support teams, asset management, or planning. The goal is to help teams get work done faster and more efficiently, using automation layered on top of your system of record.
Zero Touch Support is the “0” that focuses on service operations and is the foundation for Autonomous IT.

8. Who is the L1 IT Service Desk AI Specialist for, and what is it best at solving?

The AI Specialist is meant to be a member of the L1 service desk team and reduce the number of repetitive incidents humans have to resolve. Today it is best for incidents from deflection-less channels. In the future, the Specialist will work on more complex use cases as it learns in customer environments and will make suggestions to close knowledge gaps.

9. What is the difference between AI Specialists and Virtual Agent/chatbots?

The Virtual Agent is designed for conversational chat interfaces, like Teams, Slack, and the Virtual Agent interface on the portal or Employee Slate. While some of the functionality is similar (knowledge lookups, catalog requests, etc.), the interaction model is specifically designed for chat.
The L1 IT Service Desk AI Specialist is designed to function like a human working on Incident and Request records. Many of these incidents are created in channels with zero deflection, such as filling out a form on a portal or simply emailing IT. This is where the AI Specialist shines. It picks up these new incidents before a human does and responds to employees with helpful steps to resolve them.

10. How does the L1 IT Service Desk AI Specialist differ from EmployeeWorks?

EmployeeWorks and Autonomous Workforce aren’t competing experiences. They’re two halves of one operating model, and they meet employees wherever they want to engage. EmployeeWorks is the AI front door where every employee can search and automate tasks across systems. Autonomous Workforce is the AI labor layer that resolves the work behind that front door with governed AI Specialists.
EmployeeWorks and AI Specialists both do work, but in different ways. EmployeeWorks works with employees to find information and do work conversationally. AI Specialists resolve work autonomously, handling it as a virtual team member. The two are complementary, not competing.

Dimension	EmployeeWorks	L1 IT Service Desk AI Specialist
Entry point	Chat, portal, search	A ticket is submitted via any channel (chat, email, phone, portal, automated system triggers) and assigned to the L1 Specialist
Scope	Deflection and self-service	End-to-end incident resolution (diagnosis, fix, documentation)
Value play	Prevents ticket creation	Resolves tickets autonomously; enriches and hands off intelligently

11. What is the difference between AI Specialists and Agentic Workflows?

An AI Specialist is an autonomous worker that fills the same role as a human worker and delivers outcomes just as a human does.
An Agentic Workflow is the plan or workflow, often orchestrated by AI Specialists that have the correct context and skills equipped.

12. Do AI Specialists work on interactions?

AI Specialists are currently designed for incidents and catalog requests.
The ability for AI Specialists to review previous interaction context from chat transcripts via Moveworks and Virtual Agent is on the roadmap.

Enablement

13. Should customers engage ServiceNow’s professional services to implement the product?

Customers should contact their account team to help make the best decision on who should help them implement. They should not try to implement on their own.

14. How can I view the Specialist in action?

For a link to the YouTube playlist click HERE
For a link to the L1 IT Service Desk AI Specialist Product Doc click HERE

Solution Questions

15. What license do customers need?

ITSM Prime

16. Do CSM customers have access to the L1 IT Service Desk AI Specialist?

CSM customers can only access the Specialist via an ITSM Prime add-on for the CSM/Industry SKU.

17. What other prerequisites are needed to use the L1 IT Service Desk AI Specialist (Zero Touch Service Desk, sn_ztsd plugin)?

Platform version: Zurich Patch 10 or higher, or Australia Patch 3 or higher
Now Assist for ITSM version 15.0.10+
Service Operations Workspace ITSM (sn_sow_itsm_cont) version 9.2.0+
IT Service Management AI agent collection (sn_itsm_aia) 9.0.0+
Now Assist AI Agents (sn_aia) 8.0.10+
Now Assist for Platform (sn_genai_platform) 12.0.0+
AI Engagement Experience 3.3.2+

18. Will the L1 IT Service Desk AI Specialist have an ITIL license since it will be in the sys_user table?

No. It is a machine-type user that is not counted in licensing.

19. Will the L1 IT Service Desk AI Specialist consume an ITIL license?

No. Even though it’s in the sys_user table, it is a machine-type user that isn’t counted in licensing.

20. Is there an additional cost besides the Prime license?

There is no additional entitlement needed for functionality, but the Specialist does consume assists when it is called to do work.

21. How many assists will it consume, and is there a calculator to help customers plan?

The Specialist will consume 15 assists per assigned incident or invocation that it is supposed to attempt, per the defined routing criteria. See product docs for more information.

22. How configurable are the AI Specialists?

Please see the product documentation site for the latest configuration options.

23. Who should I reach out to if a customer runs into a technical issue with the L1 IT Service Desk AI Specialist?

Please open a support case if you run into any technical issues not covered in the documentation.

24. Does the Specialist use agentic routing (Advanced Work Assignment, AWA), and does it override the assignment?

Yes, we support both AWA and assignment rules. Customers can choose either one. The Specialist will not override any existing assignment logic. You assign incidents to the Specialist the same way you would any other member of the service desk, whether through assignment rules or manual assignment.

25. How does the Specialist re-route if it can’t fix an issue?

It synthesizes the research it has already completed and routes it back to the same assignment group for a human service desk agent to review.
The re-routing criteria can be configured to send an incident or request to a specific person or group, or back into the queue.

26. Is there a solution for managing the onboarding and offboarding lifecycle?

The Specialist can be created and configured in Agent Studio and Service Operations Workspace (SOW). Onboarding and offboarding for the service desk is done in Service Operations Workspace.

27. Can customers create their own AI Specialists? Will it require Creator licenses?

Customers can create copies of existing AI Specialists for specific service desk use cases and edit skills, roles, and access. Creating a custom Specialist from scratch is not available today.

28. What are the key things I need to know about implementing an AI Specialist?

Please see the Implementor’s Playbook in the resources section of this FAQ.

29. Is the L1 agent multilingual? What happens if the request is in a non-English language?

Support for Tier 1 languages and Japanese is expected in Q4 2026. The Specialist will be able to receive and respond in these languages.

30. How does this integrate with Moveworks AI?

An incident created by Moveworks can be picked up by the AI Specialist. We support any channel from which an incident is created.

31. How does this work with IVR partners like Genesys (omnichannel)?

Same as above. If a voice agent cannot deflect and creates an incident, it can be routed to the Specialist.

32. Are you using process mining to track resolution pathways?

Yes. Process Mining is used to review the performance of the Specialist.

33. Is this available in regulated markets?

The Specialist is available in the ServiceNow FedStore and in the GCC Internet POD. We are still testing to expand the level of certification.

34. Does the L1 IT Service Desk AI Specialist support domain separation?

Not today. Domain separation is expected to be supported in H2 2027.

35. What is the basis of the confidence score?

The score comes from referencing sources such as similar closed incidents, usage signals from knowledge articles, and known error articles.

36. What is the measured precision and recall of the L1 IT Service Desk AI Specialist?

The Specialist will answer incidents when it has high confidence. For incidents with low confidence, it will reassign them to a human service desk agent. In the AI Specialist profile, you can define where you want incidents reassigned: an assignment group or a specific person.

37. How does the AI Specialist determine solution confidence?

Before proposing a fix, the AI Specialist runs every candidate solution through an independent verification step. That step checks the solution against:
Whether it’s grounded in knowledge retrieved from the knowledge base
Whether the caller is eligible to take the required action

38. Where can we see Performance Monitoring Metric dashboards?

Because the AI Specialist is a sys_user record, if you have PA metrics with an assigned group, you should see the AI Specialist’s performance metrics inline with your existing dashboards.
Additional feedback and performance metrics are available in the Specialist profile.

39. What LLM does the L1 Service Desk AI Specialist use?

Azure OpenAI.

40. Can a customer use their own LLM to support the AI Specialist instead of Azure OpenAI?

BYOK (Bring Your Own Key): you can use your own Azure OpenAI, AWS Claude, or Google Gemini account and key.
BYOLLM (Bring Your Own LLM): you can bring and connect your own model through the Generative AI Controller.

41. Will I be able to manage the AI Specialist in AI Control Tower?

Yes. The AI Specialist has been added as an AI system you can monitor in AI Control Tower.

42. Which applications do I need to get started?

Now Assist for IT Service Management, Service Operations Workspace ITSM, Knowledge Management, and ITSM Autonomous Workforce.

43. Can the Specialist perform actions on the end user’s device?

Yes. The Specialist can perform actions such as clearing cache, killing a process, and restarting Zscaler. These actions require a ServiceNow DEX license. Actions like SharePoint permissions and Okta account management require no additional license. Currently, all L1 IT Service Desk AI Specialist actions are in controlled availability. Please contact your account team if you have further questions.

44. What are the key features of the L1 IT Service Desk AI Specialist?

End-to-end resolution. A coordinated team of specialized AI agents works together to understand the problem, find the fix, and propose the resolution to the caller. Each agent has a defined role, so the incident moves all the way to resolution without a person having to drive it.
Investigates like your best agents. It draws on knowledge base articles, past incidents, known errors, and catalog items to reach a resolution, and it asks the requester follow-up questions when it needs more information.
Request fulfillment. Some incidents come in as requests. In those cases, the system proposes or submits the appropriate request item, such as a software access request. When a person must confirm details first, it provides the exact link required instead of a dead end.
Confidence-gated action. Before it acts, the system evaluates and scores its own proposed answer. When confidence is high, it proceeds. When it is not, it continues researching or escalates. A weak or partial-match answer never reaches the caller. Instead, the incident is reassigned to a service desk agent.
Seamless reassignment to a service desk agent. When confidence falls below the defined threshold, the system reassigns the incident to the designated assignment group or person, with the full history of what it already attempted attached.
Two execution modes. Run each Specialist in autopilot, where it posts resolutions directly, or in copilot, where a person approves the resolution first. Switch between them per Specialist at any time, so you can validate behavior before granting full autonomy.
Monitor performance. Track the auto-resolution rate, how many incidents the Specialist manages through the full lifecycle, which knowledge base articles it uses to resolve them, and more.
Complete traceability. Every search and step the system performs is recorded. If a resolution falls short, your team can review exactly what happened and why, and address the root cause rather than work from assumptions.
Choose your controls. Decide how the AI Specialist handles an incident at every stage. Configure how it classifies and routes each incident, which knowledge sources it draws on, how deeply it researches, and when it steps back for a person to confirm. Sensitive or high-risk work can be held for review while routine work runs on its own.
Governed by default. The AI Specialist and its team of AI agents are automatically registered and kept current in ServiceNow’s AI Control Tower, alongside the rest of your governed systems.