Deploy AI voice agents
Summarize
Summary of Deploy AI voice agents
AI voice agents in ServiceNow are generative AI-powered conversational agents designed to enhance phone-based support with natural, dynamic interactions. They replace traditional phone menu trees with seamless, human-like conversations that help users efficiently complete tasks, resolve issues, and access information. These agents are part of the broader ServiceNow AI Platform and can be deployed from the base system or customized to fit specific business needs.
Show less
AI voice agents are managed through AI Agent Studio, which provides tools for creation, deployment, and monitoring. They operate within voice assistants, virtual help desks that can host multiple AI voice agents. Each agent is equipped with tailored AI instructions, tools, and knowledge to address user requests. Configuration options include welcome messages, voice profiles from a voice library, and fallback mechanisms such as routing to live agents or ticket creation via record producers.
Key Features
- Communication Channels: Voice assistants connect to users via telephony providers or Web Real-Time Communication (WebRTC) for mobile and web applications.
- Supported Technologies: AI voice agents support multiple Large Language Models (LLMs) including Azure OpenAI, Google Gemini, AWS Claude, and limited English support for Now LLM Service.
- Telephony Providers: Integration with several providers such as Twilio, Genesys, Amazon Connect, 3CLogic, and Five9 using protocols like WebSocket, SIP, and PSTN.
- Customization and Configuration: Ability to customize user identification, authentication, voice profiles, welcome messages, and fallback options.
- Licensing: Access to features and AI capabilities depends on your ServiceNow product tier and license.
Deployment Steps
- Install the Now Assist AI voice agents application.
- Configure user identification and authentication mechanisms.
- Create an AI voice assistant to manage interactions.
- Create and configure AI voice agents with specific capabilities.
- Test AI voice agents to ensure proper functionality.
Important Considerations
- AI Limitations: AI-generated outputs may not always be accurate or appropriate. It is crucial to test and evaluate results, maintain human oversight, and avoid sole reliance on AI for critical decisions, especially in sensitive domains like healthcare or finance.
- Data Processing and Privacy: Data from customer instances may be transferred to centralized ServiceNow environments or third-party cloud providers. ServiceNow handles data according to internal policies and compliance standards.
- Data Collection: ServiceNow collects inputs, outputs, and edits to improve AI technologies but customers can opt out of data collection at any time.
- Compliance: Users must comply with applicable privacy, recording consent, and anti-wiretapping laws when deploying AI voice agents.
AI voice agents are generative AI-powered agents that bring natural, conversational experiences to phone-based support. As part of the broader AI agent ecosystem, they connect with telephony providers to replace rigid menu trees with seamless and human-like interactions that can help make support faster and more intuitive.
AI voice agents overview
AI voice agents use generative AI to deliver natural, dynamic conversations that help users complete tasks, resolve issues, and access information.
AI voice agents are part of the ServiceNow AI Platform capabilities and can be deployed from the base system or customized to meet specific business needs. AI voice agents are managed through the AI Agent Studio, which provides tools for creating, deploying, and monitoring AI voice agents.
AI voice agents are associated with voice assistants, which act as a virtual help desk. A voice assistant can host multiple AI voice agents. Each AI voice agent is equipped with specific AI instructions, tools, and knowledge to resolve user issues. You can configure welcome messages, select voice profiles from the voice library, and define fallback options like live agent routing or record producer-based ticket creation.
When you create or edit a voice assistant, you configure communication channels to define how the voice assistant connects to users. Communication channels are organised into two tabs:
- Telephony provider — connects the voice service to phone networks. Select a communication channel type, then select a CCaaS provider.
- Web Real-Time Communication (WebRTC) — connects the voice service to mobile applications.
- LLMs (large language model): Azure OpenAI, Google Gemini, and AWS Claude. Now LLM Service is also supported but limited to English language only.
- Telephony providers: Twilio (WebSocket), Genesys (WebSocket and SIP), Amazon Connect (PSTN), 3CLogic (WebSocket), and Five9 (SIP). Mobile and web applications are supported through the Web Real-Time Communication (WebRTC) channel.
Deploying AI voice agents
AI limitations
This application uses artificial intelligence (AI) and machine learning, which are rapidly evolving fields of study that generate predictions based on patterns in data. As a result, this application may not always produce accurate, complete, or appropriate information. Furthermore, there is no guarantee that this application has been fully trained or tested for your use case. To mitigate these issues, it is your responsibility to test and evaluate your use of this application for accuracy, harm, and appropriateness for your use case, employ human oversight of output, and refrain from relying solely on AI-generated outputs for decision-making purposes. This is especially important if you choose to deploy this application in areas with consequential impacts such as healthcare, finance, legal, employment, security, or infrastructure. You agree to abide by ServiceNow’s AI Acceptable Use Policy, which may be updated by ServiceNow.
Data processing
This application requires data to be transferred from ServiceNow customers' individual instances to a centralized ServiceNow environment, which may be located in a different data center region from the one where your instance is, and potentially to a third-party cloud provider, such as Microsoft Azure. This data is handled per ServiceNow's internal policies and procedures, including our policies available through our CORE Compliance Portal.
Data collection
ServiceNow collects and uses the inputs, outputs, and edits to outputs of this application to develop and improve ServiceNow technologies including ServiceNow models and AI products. Customers can opt out of future data collection at any time, as described in the Now Assist Opt-Out page.
For more information, see the Now Assist documentation.
Privacy notice
By using this feature, you confirm that your use (including use by your service providers) complies with relevant anti-wiretapping, recording consent, and other privacy laws, as applicable.