Brazil, Australia Patch 5, Australia Patch 3, Zurich Patch 12, Zurich Patch 10
Generative AI
The L1 IT Service Desk AI specialist will autonomously resolve high-volume, routine issues by triaging the incident, identifying the issue, researching the resolution, and resolving it end-to-end. It runs inside ServiceNow workflows you already operate, follows the policies and guardrails you set, and reassigns the moment something falls outside what it's cleared to handle.
Getting Started:
- Implement with a ServiceNow expert. Please reach out to your account representative to plan your implementation with a ServiceNow professional implementation expert. This will ensure proper configuration of triage, knowledge sources, confidence thresholds, and governance to make autonomous resolution safe and effective in your environment.
- Identify the right candidates first. Before deployment, use the L1 IT Service Desk AI Specialist Onboarding Tool to determine which clusters are primed for autonomous resolution. It assesses your environment and pinpoints where the AI Specialist will perform well based on your KB and catalog coverage, so you start with high-confidence use cases and expand from there.
- 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 asks the requester follow-up questions when it needs more to go on.
- 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 the AI Specialists' performance. Track its auto-resolution rate, how many incidents it 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 is automatically registered and kept current in ServiceNow's AI Control Tower, alongside the rest of your governed systems.
New
- Service Desk Managers get a Rate trend chart on the AI Specialist Performance dashboard plotting the durable auto-resolve and coverage rates over time, with each day's incidents a click away.
- Service Desk Managers get a four-step funnel on the Overview tab, from incidents assigned to eligible groups to incidents durably resolved, with drill-down and cards explaining each rate.
- Service Desk Managers get a chart of what the service desk did with cross-group reassignment recommendations: adopted, overridden, or awaiting a decision.
- AI Admins can set the portal that knowledge and catalog links open for requesters, while Service Desk Agents keep platform links in work notes.
- Requesters see the catalog item variables the AI Specialist submitted in the Solution Proposed comment.
Changed
- Requesters are asked fewer catalog questions, because the AI Specialist fills variables from the incident and the caller's details and shows what it already captured.
- Requesters receive catalog follow-up questions composed from instruction-mode templates, with the fixed template as a fallback.
- Service Desk Agents see a knowledge article in Attached Knowledge only once the incident it resolved is closed.
- Service Desk Managers can apply the Assignment Group and AI Specialist filters together on the All incident outcomes chart.
- Service Desk Managers on non-English instances see the Catalog tab, funnel, cross-group outcomes, and catalog indicators in their own language, in up to 24 locales.
Fixed
- Access control gaps let users or prompt-injected tool calls read records beyond their permissions through the Catalog Agent and the AI Specialist's tools, and let generative AI steps run without checking the triggering user's access.
- Cited knowledge articles were dropped from requester comments by a faulty access check, and were missing from work notes after a low-confidence fallback or reassignment.
- Saving activity notes failed when research included an uncited result from a table the AI Specialist cannot read.
- Knowledge and catalog links in Helpful References opened the platform view instead of the portal.
- Resolution notes were cut off at the Helpful References section when none of its links remained.
- A knowledge feedback task was created for incidents resolved with a catalog item.
- Incidents stayed In Progress when the Solution proposed state was mapped to Resolved or Closed.
- A requester comment arriving just after work started could start a duplicate run on the same incident.
- The closing note after a requester confirmed the fix was always written in English.
- Canadian French was treated as French.
- Notes could post with template slots unfilled. The AI Specialist now retries and hands off to a person after three failures.
- The AI Specialist could ignore the operating system of the computer linked to the incident.
- Reloading a dashboard drilldown page failed, and unused article links opened a not found page.
- After an upgrade to version 1.2.2, the dashboard could be missing earlier improvements and show identical first two routing journey metrics.
- Attachment summarization did not work out of the box, because its service URL property shipped empty.
- A deprecated AI agent could run instead of the AI Specialist agent after an upgrade.
Removed
- The Routing journey count cards are gone from the Detailed view, replaced by the Overview funnel.
- The unused Research depth setting is gone.
- The Pre resolution condition setting is gone, and incidents are no longer checked against it.
Not applicable for this application version. For more information, please see
Application Runtime Policy
IT Service Management Prime
Otto for IT Service Management
Australia Patch 3+ or Zurich Patch 10+
Other Requirements:This version does not support GCC environments
This version does not support Domain Separation