AI Agents FAQ What’s an AI Agent at ServiceNow? AI agents are autonomous systems that interact with their environment to gather data, make decisions, and complete tasks that would otherwise need to be done by a human. What license do I need to use Now Assist AI Agents? You need a Pro Plus or Enterprise Plus SKU to use AI Agents, or an AI SKU such as Foundation, Advanced or Prime. Prime is required to create or significantly modify AI Agents. What are the prerequisites to install and use AI Agents? Customers must have Now Assist installed with a Pro Plus/Enterprise Plus entitlement. They must be on Zurich Patch 1+ (Australia+ recommended), with the ServiceNow Otto for ITSM, HRSD..., and AI Agents store apps installed. Admins must have the sn_aia.admin role. AI Search and Otto (Now Assist) Panel must also be enabled. The latest store app version as of July 2026 is 8.1.7. You may also install the Otto AI Agents store app via the Now Assist Suite bundle. Is my instance ready for AI Agents? Use the Now Assist Readiness Evaluation store app, which is a tool to determine your instance health for AI Agents. What’s an agentic workflow vs agent vs tools? An agentic workflow is the overall business problem or goal you’re trying to solve. Think of it as the why—the reason you’re deploying AI agents. An agent is the who—the virtual worker that performs specific tasks to help achieve the use case. Tools are the operations run to perform actions. They are usable by AI Agents to perform their tasks and achieve the use case. What LLM(s) does AI Agents use? AI Agents uses Azure OpenAI's GPT-5.5 by default for its orchestration layer on ServiceNow managed Azure servers. The pre-configured context window for the AI agent is 128K tokens (exceeding this may lead to unpredictable behavior). The orchestrator LLM can also be configured to use other models such as NowLLM, Claude, and Gemini. Using a third party model hosted by ServiceNow does not create additional charges with that model. Note that using BYOK or integrating with a separate agent or model not hosted by ServiceNow may create additional charges. What's the longest I can make AI Agent instructions? The max length for an AI Agent Role: Max Length = 2,000. For AI Agent Instructions: Max Length = 8,000 Can AI Agents connect to 3rd party LLM or agents? AI Agents can connect to 3rd party LLMs and other systems (including agents) via the subflows/actions tools as an integration. More seamless communication between ServiceNow agents and external agents such as MCP and A2A is also available. How does AI Agents consume assists? Assist consumption pricing is based on number of actions that are run, not including the orchestrator or communicator agent actions. AI Agents are bucketed into "Small", "Medium", and "Large". See our assists overview for more information: ServiceNow Assists Overview. Sub-prod usage and testing in AI Agent Studio also consume assists. You can monitor agentic assists consumption in the AI Agent Studio analytics page. See this article for how to manage agentic assists consumption: Manage your agentic assists consumption with these AI Agent properties Do skills and Virtual Agent topics run in agentic workflow still consume assists? No. If a skill, Virtual Agent topic, or conversational catalog item is run in an agentic workflow as a tool, it does not consume assists. The agentic workflow run itself would still consume assists per the "Small", "Medium", "Large" guidelines. (Skills are not counted when run in Now Assist in Virtual Agent or Now Assist Panel either.) However, if a skill is embedded in a script or workflow tool, it will consume assists. Are AI Agents available in a PDI? No. How do we prevent hallucinations? Humans are still involved when AI Agents are running. AI Agents introduce the concept of "human on the loop" systems where humans primarily monitor the AI's actions and only intervene when necessary, taking a more supervisory role rather than actively contributing to decisions. For example, human service agents can review an AI Agent-generated plan and provide feedback or explicit approval before execution or changes. We also provide prompt injection protection via Now Assist Guardian. Our grounded prompt templates tie the prompts to platform data and increase the accuracy of the response, as well as RAG. Customers can use the same in Now Assist Skill Kit for Skills as tools; and set the temperature to ensure the output is more grounded. Note that with any generative AI product, hallucinations are a possibility. How are AI Agents triggered? AI agent builders can create triggers when creating an AI Agent or Agentic workflow that calls the agent when a condition or objective is observed. Agents can also be triggered via database changes or a user query. Is feedback given back to AI Agents used at all? During an AI agent interaction, the AI agent may ask the human user for feedback and/or permission to proceed. The AI Agent then may change its approach depending on the feedback. Do AI Agents recognize ServiceNow objects in its instructions? (Table names, field names...) Yes, it can. What languages are supported by AI Agents? AI Agents is available for all instance-supported languages. Does AI Agents support domain separation? Yes. The sys_domain field exists on all agent tables and will get the sys_domain_path if the domain separation is enabled in the instance. Can data be passed between different tools and different AI Agents? Data in an agentic workflow conversation is stored in short term memory and can be passed between tools via the Agent's instructions. It can also be passed between AI Agents via instructions. Note that the data is being transferred by the LLM and may be changed. To minimize this, in the instructions, tell the Agents to be exact in passing the data. Also in the Tools UI, change the LLM strategy to ‘None’. What are the out-of-box agents available? Workflows such as ITSM, HRSD, and CRM are each shipping out-of-box agents to provide out-of-box content and experiences for customers. You can find the list of OOB AI Agents here: Link. More out-of-box agents will be shipped in future releases. I'm getting a “No agents are available at the moment” error message. How do I fix this? This is usually due to the Agent proficiency not being filled out or inaccurate. There could be several reasons: AI Search is not enabled, the token count for the orchestrator has been exceeded, the agent prompt(s) is not descriptive enough. Also check that the AI Agents and tools such as Skills are all Active. AI Agent states that it can no longer execute a tool Check the property value for “sn_aia.continuous_tool_execution_limit”. This property controls the maximum limit for continuous, uninterrupted executions for the same tool. Can Now Assist in Virtual Agent run an agentic workflow? Can it run AI Agents? Yes, Now Assist in Virtual Agent can run AI Agents. You can't discover an agentic workflow in Virtual Agent (if you type "help resolve INCxxx", nothing will happen.) You can only trigger an agentic workflow to appear in Now Assist in VA (create an INC, then an agentic workflow will run in Virtual Agent). Be sure the "Agentic Support" toggle is activated in the “Assistants > Settings” setup page. In the AI Agent Studio, ensure that the Virtual Agent experience is toggled on for the AI Agent. Also make sure that your AI Agent description and role is detailed so that it can match the user query. The model provider for the AI Agents skill group is recommended to be Azure OpenAI. The Now Assist Panel times out after 2 hours Check the value for “Conversation Idle Timeout” for the Now Assist Panel (sys_cs_channel) record. Also check the property value for “com.glide.cs.conversation_idle_timeout”. Note that this property is Global and not specific to the Now Assist AI Agents, but rather to Virtual Agent as a whole. How do I ensure that my AI Agents are performant? If you are building agents that need to analyze a lot of data, use Skill Kit to build a skill that the agent can use to speed up the agent and limit it’s LLM calls. The more tools and agents contained within a use case, orchestration performance may differ (we don't recommend >15 tools). How do I evaluate the performance of an AI Agent before going to production? AI Agent Studio includes an Agentic Evaluation tool. You create an evaluation job, define a dataset of representative historical records (recommended: 20–100 records), and run the evaluation. The framework executes the agent against each record, collects execution logs, and scores results across metrics such as task completeness, tool calling correctness, and faithfulness. My AI Agent isn't consistent and does different things each time. AI Agents and generative AI are non-deterministic systems. Running the same thing twice might give different results due to the LLM and instructions. How do I learn more about ServiceNow AI Agents? View our documentation at: Link. A Now Learning course on AI Agents is available here: Now Learning. To learn more about prompting AI Agents, see this prompting guide: Now Assist AI Agents prompting guide. Learn how to quickly set up AI Agents with the Agentic workflows End to End Setup Guide.