# ServiceNow AI Agents AI agents on the ServiceNow AI Platform that work in teams through an orchestrator and agentic workflows to run tasks in IT, customer service and HR. Canonical profile: https://ki-agentenkompass.de/en/agents/servicenow-ai-agents/ Editor: [Michael Meierhoff](https://ki-agentenkompass.de/en/about/) Sources reviewed: 2026-11-05 Basis: provider documentation. Examples are editorial suggestions, not hands-on product tests. ## Overview The name ServiceNow AI Agents is current on the product page. Since May 2026, ServiceNow Otto has been the shared AI experience that routes requests to agents and combines Now Assist, Moveworks and AI Experience. The former AI Control Tower is called Super Intelligence Control Tower on the product page, and the old address redirects there; community posts sometimes still use the old name. - Provider: ServiceNow - Product family: ServiceNow AI Agents - Profile type: Agents and orchestration on an enterprise platform - Environment: On the ServiceNow AI Platform, reached through ServiceNow Otto; according to the product page also by phone, browser and desktop apps as voice, web and desktop agents - Connections: Action Fabric with A2A and MCP client; tools such as flow actions, subflows, scripts and skills - Setup: Requires a ServiceNow instance and a matching licence. You activate prebuilt agents and build your own in AI Agent Studio using natural language. The entry point is a demo or quote. - Pricing model: No public prices; the ITSM pricing page shows packages and a custom quote. According to employee posts, usage is measured in assists. ## Key features ### Agentic workflows An agentic workflow describes the business goal, such as triaging cases. According to the product page, agents plan tasks for it, use tools and adapt their approach. Source: https://www.servicenow.com/products/ai-agents.html ### AI Agent Orchestrator Coordinates teams of agents towards shared goals. Source: https://www.servicenow.com/products/ai-agents.html ### AI Agent Studio You build and customize your own agents in natural language and set guardrails. According to the page, AI Agent Advisor suggests use cases from your data. Source: https://www.servicenow.com/products/ai-agents.html ### Action Fabric Connects third-party agents and tools: A2A for communication between agents, an MCP client for external tools and data. Source: https://www.servicenow.com/products/ai-agents.html ### Voice, web and desktop agents The product page names agents for phone, mobile and web, for browser-based apps and for desktop apps without an API. Source: https://www.servicenow.com/products/ai-agents.html ### Super Intelligence Control Tower Central place to inventory, secure and measure AI agents, including third-party ones. The page names a kill switch and the AI Passport as proof of identity and permissions. Source: https://www.servicenow.com/products/super-intelligence-control-tower.html ## Example workflows ### Triage incidents - Your input: New incidents in ITSM and an agentic workflow triggered when a record is created. - Possible result: Agents classify incidents and prepare next steps. - What to check: Set high-risk tools to "Supervised" and check the trigger for recursion risk. ### Build a custom agent with role masking - Your input: A role description in natural language and matching flow actions in AI Agent Studio. - Possible result: An agent that works within the masked roles of the calling user. - What to check: Check the licence tier, role mask and assist consumption during testing. ## Requirements and limits ### Licence and instance Requirement: According to an employee FAQ you need Pro Plus, Enterprise Plus or an AI package such as Foundation, Advanced or Prime. Prime is said to be required to create or significantly change agents. Source: https://www.servicenow.com/community/now-assist-articles/ai-agents-faq-and-troubleshooting/ta-p/3200454 ### Consumption during testing too Limitation: According to an employee FAQ, non-production use and tests in AI Agent Studio also consume assists. Source: https://www.servicenow.com/community/now-assist-articles/ai-agents-faq-and-troubleshooting/ta-p/3200454 ### Agents are not deterministic Limitation: According to an employee FAQ, the same input can lead to different results. Data passed on by the model can change in the process. Source: https://www.servicenow.com/community/now-assist-articles/ai-agents-faq-and-troubleshooting/ta-p/3200454 ### Rollout of Otto Not yet confirmed: According to the press release, Otto starts through EmployeeWorks and the Control Tower and is due to reach all products in the following year. It does not say which instance gets what and when. Source: https://newsroom.servicenow.com/press-releases/details/2026/ServiceNow-Otto-creates-the-unified-AI-experience-for-the-enterprise/default.aspx ### Model default Not yet confirmed: According to an employee post, since 9 July 2026 prebuilt agents without a fixed model choice move to third-party providers with the store update. The post does not say which provider applies to which agent. Source: https://www.servicenow.com/community/servicenow-otto-articles/third-party-model-providers-are-the-recommended-defaults-for/ta-p/3560810 ## A good fit if … - your IT, service or HR workflows already run on ServiceNow - you want to control agents with role masks and an approval mode per tool - you want to inventory and secure your own and third-party AI agents in one place ## Less suitable if … - you have no ServiceNow instance and want to get started quickly on your own - you need public prices or fixed costs per run - you want to check data paths without access to the support portal Editorial assessment based on provider documentation. Not a product test. ## Usable AI models Fixed choice across providers The ServiceNow docs list the Now LLM Service, Azure OpenAI, Google Gemini and Claude via AWS for skills and AI agents. Admins define the allowed options in AI Control Tower and set preferences per skill in the Now Assist Admin Console. Not all providers are available with in-country contracts. - Model families named: In-house model, OpenAI (GPT), Google (Gemini), Anthropic (Claude) - Model choice: You choose - Your own API key: Not stated - Router or custom endpoint: Not stated - Local models: Not stated - Depends on: Admin approval, Region Partly documented · Sources accessed on: 2026-11-05 - [ServiceNow Docs: Yokohama TMT, PDF](https://downloads.docs.servicenow.com/pdf/enus/servicenow-yokohama-telecom-media-technology-enus.pdf) - [ServiceNow: Otto press release](https://newsroom.servicenow.com/press-releases/details/2026/ServiceNow-Otto-creates-the-unified-AI-experience-for-the-enterprise/default.aspx) ## Europe & regional availability Support article KB2689562 on data residency and privacy for AI showed only a loading message when retrieved. The white paper on the ServiceNow Protected Platform for the EU could not be retrieved. Neither is therefore evaluated. Reviewed scope: Hosted platform; European data paths for AI open Reviewed on: 2026-11-05 ### Protected Platform for the EU Availability still unclear An employee post says SPP EU customers use the same regional deployments as commercial EMEA customers. It does not explain how third-party providers handle data location for these customers. Region covered: EU Documented reason: The white paper could not be read, so conditions and scope remain unchecked. Official source: https://www.servicenow.com/community/servicenow-otto-articles/third-party-model-providers-are-the-recommended-defaults-for/ta-p/3560810 ### Model choice and providers Availability still unclear According to an employee post, prebuilt agents move to Azure OpenAI, AWS Claude or Google Gemini. At instance level you can return to Now LLM Service in AI Admin Hub. Data residency can limit the choice. Region covered: EU/EEA, United Kingdom and Switzerland Documented reason: Depends on configuration and provider; the post does not give the regions per provider. Official source: https://www.servicenow.com/community/servicenow-otto-articles/third-party-model-providers-are-the-recommended-defaults-for/ta-p/3560810 ### EU AI Act in the Control Tower Availability still unclear According to its page, the Control Tower includes content for the EU AI Act. This says nothing about the availability or data location of agents in Europe. Region covered: EU Documented reason: This is governance content, not a regional statement. Official source: https://www.servicenow.com/products/super-intelligence-control-tower.html ## Accounts & permissions Based on provider documentation. Permissions depend on the account, integration and organization policies. Review the permissions actually requested before use. Configuration covered: Vendor platform with role control in the instance Sources reviewed: 2026-11-05 ### Account used Documented with conditions: According to an employee post, agents run as a dynamic user with the caller's rights (default) or as an AI user with its own roles. The Control Tower names the AI Passport as a signed proof. The reviewed pages do not describe SSO. Evidence: https://www.servicenow.com/community/servicenow-otto-articles/latest-access-control-security-enhancements-for-ai-agents-and/ta-p/3374036 Evidence: https://www.servicenow.com/products/super-intelligence-control-tower.html ### Admin approval Documented: According to an employee guide, each tool has Supervised and Autonomous modes. Supervised requires human oversight and is recommended for sensitive actions. Evidence: https://www.servicenow.com/community/servicenow-otto-articles/servicenow-ai-agents-build-operations-amp-governance-guide/ta-p/3569932 Evidence: https://www.servicenow.com/community/servicenow-otto-articles/latest-access-control-security-enhancements-for-ai-agents-and/ta-p/3374036 ### Data access & team sharing Documented: According to the post, role configuration and role masking are mandatory and limit workflow, agent and tool in sequence. Tools are checked against the run-as identity. Evidence: https://www.servicenow.com/community/servicenow-otto-articles/latest-access-control-security-enhancements-for-ai-agents-and/ta-p/3374036 ## Prices and included usage Pricing checked: 2026-11-05 No public prices. The ITSM pricing page shows Foundation, Advanced and Prime and only offers "Get Custom Quote". ### ITSM Foundation No public price; custom quote According to the page, agents and skills for task-based support. Price source: https://www.servicenow.com/products/itsm/pricing.html ### ITSM Advanced No public price; custom quote According to the page, agentic workflows and AI Voice Agents. Price source: https://www.servicenow.com/products/itsm/pricing.html ### ITSM Prime No public price; custom quote According to the page, AI Specialists and AI Agents for ITSM. Price source: https://www.servicenow.com/products/itsm/pricing.html Packages of other products were not reviewed. An employee guide names 25 assists for agentic workflows with 0 to 4 tools, 50 with 5 to 8 and 150 with 9 to 20. This is no price list, and it gives no assist prices. Third-party pricing was not used as evidence. Pricing details: https://www.servicenow.com/products/itsm/pricing.html ## Operation & oversight Based on public provider documentation. Assessments are editorial inferences from the stated properties. Actual time requirements and reliability have not been measured. Deployment covered: Operation in the ServiceNow instance; models from ServiceNow or third parties depending on configuration Sources reviewed: 2026-11-05 ### Files and working state Documented with conditions: According to an employee FAQ, the execution plan and tasks are stored in instance tables (sn_aia_execution_plan, sn_aia_execution_task). The reviewed pages give no retention periods. Evidence: https://www.servicenow.com/community/now-assist-articles/ai-agents-faq-and-troubleshooting/ta-p/3200454 ### Sign-ins Documented with conditions: The agent runs as a dynamic user or AI user. The reviewed pages do not describe how external tools manage credentials or which SSO applies. Evidence: https://www.servicenow.com/community/servicenow-otto-articles/latest-access-control-security-enhancements-for-ai-agents-and/ta-p/3374036 ### Starting further runs Documented: The employee guide names triggers on record creation or update, on a schedule and on inbound email, plus manual start in the Otto panel. It warns about recursion and names limits. Evidence: https://www.servicenow.com/community/servicenow-otto-articles/servicenow-ai-agents-build-operations-amp-governance-guide/ta-p/3569932 ### Human intervention Documented: Supervised mode per tool; according to the FAQ, a service agent can review the plan beforehand, and agents ask for feedback or permission during the run. According to its page, the Control Tower has a kill switch. Evidence: https://www.servicenow.com/community/servicenow-otto-articles/servicenow-ai-agents-build-operations-amp-governance-guide/ta-p/3569932 Evidence: https://www.servicenow.com/community/now-assist-articles/ai-agents-faq-and-troubleshooting/ta-p/3200454 Evidence: https://www.servicenow.com/products/super-intelligence-control-tower.html ### Detecting errors Documented: According to the FAQ and guide, execution tables, the test panel, system logs and AI Agent Analytics help. The guide warns that with wrong run-as permissions an action can fail silently. Evidence: https://www.servicenow.com/community/now-assist-articles/ai-agents-faq-and-troubleshooting/ta-p/3200454 Evidence: https://www.servicenow.com/community/servicenow-otto-articles/servicenow-ai-agents-build-operations-amp-governance-guide/ta-p/3569932 Evidence: https://www.servicenow.com/products/super-intelligence-control-tower.html ### Resuming after failures Open in reviewed sources: The FAQ and guide do not describe automatic retries or resuming. The guide only names emergency steps: deactivate the trigger and cancel stuck plans. Evidence: https://www.servicenow.com/community/now-assist-articles/ai-agents-faq-and-troubleshooting/ta-p/3200454 Evidence: https://www.servicenow.com/community/servicenow-otto-articles/servicenow-ai-agents-build-operations-amp-governance-guide/ta-p/3569932 ### Editorial assessment Permissions, approvals and logs are described in detail, but often in community articles by employees. You need to check resuming, retention periods and data paths in the documentation, support articles and contract. ## Memory and conversation continuity Scope: Short-term and long-term memory according to employee posts Sources accessed: 2026-11-05 Short-term memory applies per conversation; long-term memory is stored in sn_aia_memory and controlled through properties; official documentation could not be read. ### Storage and scope Documented: Short-term memory applies to one conversation and is shared between agents. Long-term memory persists across sessions in the sn_aia_memory table, in vector format. - [ServiceNow Community: AI Agents Build, Operations & Governance Guide](https://www.servicenow.com/community/servicenow-otto-articles/servicenow-ai-agents-build-operations-amp-governance-guide/ta-p/3569932) ### Selection and timing Documented: Properties turn on long-term memory. sn_aia_ltm_category defines which kinds of information may be stored, such as device preferences. - [ServiceNow Community: AI Agents Build, Operations & Governance Guide](https://www.servicenow.com/community/servicenow-otto-articles/servicenow-ai-agents-build-operations-amp-governance-guide/ta-p/3569932) ### Inspect, edit and delete Partly documented: Admins and developers review and configure categories. The guide names no interface where end users view or delete their own entries. - [ServiceNow Community: AI Agents Build, Operations & Governance Guide](https://www.servicenow.com/community/servicenow-otto-articles/servicenow-ai-agents-build-operations-amp-governance-guide/ta-p/3569932) ### Agent and channel boundaries Partly documented: sn_aia_ltm_category_mapping controls which agents access which categories. The guide does not describe boundaries between channels. - [ServiceNow Community: AI Agents Build, Operations & Governance Guide](https://www.servicenow.com/community/servicenow-otto-articles/servicenow-ai-agents-build-operations-amp-governance-guide/ta-p/3569932) ### Retrieval Partly documented: The guide names the vector format and the property for use in the agent. It does not say how entries are selected or weighted. - [ServiceNow Community: AI Agents Build, Operations & Governance Guide](https://www.servicenow.com/community/servicenow-otto-articles/servicenow-ai-agents-build-operations-amp-governance-guide/ta-p/3569932) ### Session reset and compaction Partly documented: According to the FAQ, context is passed on in short-term memory, and the context window is 128K tokens; exceeding it can cause unpredictable behaviour. The FAQ does not mention reset or compaction. - [ServiceNow Community: AI Agents FAQ and Troubleshooting](https://www.servicenow.com/community/now-assist-articles/ai-agents-faq-and-troubleshooting/ta-p/3200454) ## Context A ServiceNow licence; according to an employee FAQ, the Prime package to create or significantly change agents. Official documentation pages could not be read, and many operating details come from community articles by ServiceNow employees. Product pages, the ITSM pricing page and the Otto press release reviewed. Technical details come from community articles marked "ServiceNow Employee"; they are not official documentation, and one author explicitly calls his governance recommendations his own. The support article on data residency (KB2689562) and the SPP EU white paper could not be read. Example tasks are editorial. Hands-on tests are still pending. ## Open points Europe, availability still unclear: - Protected Platform for the EU - Model choice and providers - EU AI Act in the Control Tower Requirements and limits, not yet confirmed: - Rollout of Otto - Model default ## Sources - https://www.servicenow.com/products/ai-agents.html - https://www.servicenow.com/products/super-intelligence-control-tower.html - https://www.servicenow.com/products/itsm/pricing.html - https://newsroom.servicenow.com/press-releases/details/2026/ServiceNow-Otto-creates-the-unified-AI-experience-for-the-enterprise/default.aspx - https://www.servicenow.com/community/servicenow-otto-articles/servicenow-ai-agents-build-operations-amp-governance-guide/ta-p/3569932 - https://www.servicenow.com/community/servicenow-otto-articles/latest-access-control-security-enhancements-for-ai-agents-and/ta-p/3374036 - https://www.servicenow.com/community/now-assist-articles/ai-agents-faq-and-troubleshooting/ta-p/3200454 - https://www.servicenow.com/community/servicenow-otto-articles/third-party-model-providers-are-the-recommended-defaults-for/ta-p/3560810 - https://www.servicenow.com/community/developer-blog/servicenow-otto-has-arrived-what-s-changing-in-community-and/ba-p/3591256 ## Provider ServiceNow offers a platform for enterprise workflows with integrated AI agents. - Operator: ServiceNow - Organization: Provider - Website: https://www.servicenow.com - Reviewed: 2026-11-05 - Provider source: https://www.servicenow.com/products/ai-agents.html [Sources and method](https://ki-agentenkompass.de/en/sources/)