Now Assist AI agents capabilities
Summarize
Summary of Now Assist AI agents capabilities
Now Assist AI agents in the Zurich release empower ServiceNow customers with advanced AI-driven conversational capabilities integrated within the Workspace. These agents can be invoked and managed through the AI Agent Background Channel and Provider, enabling seamless execution of AI workflows either interactively or non-interactively.
Show less
Key Features
- AI Agent Background Channel and Provider: Utilizes the Custom Adapter Framework from Virtual Agent to invoke AI agent conversations. Customers can create channel identifiers for custom chat integrations, allowing flexible inbound ID configurations to enrich conversational functionality.
- Invocation API: Conversations are started programmatically via the
snaia.AiAgentRunttimeUtil().startAiAgentConversation(request)API within a Script Include, enabling automated control of AI agent execution flows. - Execution Logging and Monitoring: All invoked AI agent conversations are logged in the Execution Plans [snaiaexecutionplan] table. Customers can review execution tasks, messages, and tool executions to audit and troubleshoot AI workflows through detailed records and AI Agent Studio Testing.
- Interactive vs Non-interactive Agents: Interactive agents actively engage users to collect missing information upon fallback scenarios, whereas non-interactive agents proceed without user input, adjusting prompts dynamically using the ReAct layer. Execution modes are configurable per conversation, allowing concurrent runs in the background channel compatible with various chat panels including Now Assist and Virtual Agent.
- Multilingual Support: AI agents support multiple languages, enhancing translation quality through tuned system prompts, dynamic translation strategies, and extensive automated and manual testing. This ensures consistent and native-like conversational experiences across different languages.
What Customers Can Expect
- Robust integration of AI agents within ServiceNow Workspace that can be tailored to specific conversational needs with custom provider configurations.
- Flexibility to run AI agents in interactive or non-interactive modes, optimizing user engagement and automation as required.
- Comprehensive visibility into AI agent executions, facilitating monitoring, debugging, and improvement of AI-driven processes.
- Enhanced multilingual conversational capabilities to support global user bases with improved translation accuracy and adaptability.
Lists the features supported by Now Assist AI agents, including configuration options and functional capabilities.
Invoke conversations with AI Agent Background Channel
The AI Agent Background Channel helps you to invoke AI Agent or agentic workflow execution from the Workspace. Use the AI Agent Background Channel associated with the AI Agent Background Provider to invoke conversations. The AI Agent Background Provider is based on the Custom Adapter Framework from Virtual Agent. For more information, see Configure a provider for your custom chat integration.
Create a channel identifier in the Provider Channel Identities table [sys_cs_provider_application] to add any additional conversational capabilities to your own provider application and get a new inbound ID that allows for customization. For more information, see Create a channel identifier for your custom chat integration.
To start a conversation, trigger the flow using the sn_aia.AiAgentRunttimeUtil().startAiAgentConversation(request) API in the Script Include (sys_script_include) of the AIAgentBackgroundProvider and select Run Script. When the Script execution status indicates Success, the conversation begins in the order of utterances defined in the Script.
Conversations that are invoked for executing an AI agent are logged in the Execution Plans [sn_aia_execution_plan] table. Open the conversation record to confirm the device type as AI Agent Background. Open the execution record to see the Execution Tasks, Messages, and the Tools Executions used to execute the AI agent.
You can also see the entire execution steps on the AI Agent Studio Testing page by copying the execution plan record's [sys_Id] and testing it. On the Chat responses tab, in the AI agent decision logs, you can see the AI agent details and the tools it used to resolve the issue.
Interactive and Non-interactive AI agents
The Interactive AI agents reach out to users for information when there is a fallback in the execution process, and the AI agent re-triggers the flow.
The Non-interactive AI agents do not reach out to the user at any fallback stage in the execution process. When the AI agent needs user information, it takes the dynamic prompt approach using the ReAct layer, where the prompt of the ReAct will change based on the execution mode of the AI agent or agentic workflow. Therefore, in the Non-interactive execution, the reach fallback options do not have to collect input from a user as a fallback option. However, the output of the AI agent or agentic workflow will still need to be presented to the user, and in any execution failure scenario, a message in the Now Assist panel or Virtual Agent is shown.
To implement the Non-interactive execution, the Execution Mode field is added in the Execution Plans [sn_aia_execution_plan] table, where the execution mode can be Interactive or Non Interactive based on the given runtime parameter.
You can run the AI agents and agentic workflows concurrently in the AI Agent Background Channel and in Non-interactive mode where the background execution allows AI agents to operate with any chat panel like Now Assist panel or Virtual Agent.
Multilingual support
- Tune system prompts for native translations.
- Implement dynamic translation strategies when native support is unavailable.
- Provide extensive testing via automated and manual evaluations.