Regal Voice Inc., an enterprise artificial voice intelligence company, today added goal-oriented agents to its platform, allowing businesses to define what a call should do and deploy two AI models that split the work of getting there.
The new agents are targeting a problem that Regal says comes up in calls like car insurance claims, where someone reporting an accident tends to explain all at once what happened, where and who was involved. Agents that rely on conditional logic often ask for details that the caller has already provided, just to have every field filled out. Building the entire agent around a single prompt keeps the conversation open, and Regal believes business processes are only loosely followed.
Goal-oriented agents use two models on every call. Regal calls them an actor and a director, and they both start working as soon as the caller stops talking. The actor, a smaller and faster model tuned to dialogue, responds immediately. In the background, the director checks whether the goals for the current phase have been met and can move the call to a new phase with new instructions for the actor.
Companies build the agents from goal nodes, each listing the goals to be achieved by the end of the node and any prerequisites that come first. Booking a callback can be one of these goals. A prerequisite is something the agent must determine before acting, such as the caller’s date of birth. Regal said these conditions could also be stated in simple language, for example, “The caller mentioned a death in the family.”
The director checks progress after each round so that one answer can tick off multiple items at once. In Regal’s sample car insurance claim, a caller named Dan describes the vehicle damage, photographic evidence, and injuries in his first message. All three are marked as picked up and the agent goes straight to his name. Once this happens, the director sees that the location and policy number are still missing, so the actor’s next question is where is he?
According to Regal, complex admissions and qualification interviews are among the agents’ strongest areas of application. The company called Medicare Enrollment, Roadside Assistance and Mortgage Qualification uses the design. Another consideration is medical enrollment, which complies with the Health Insurance Portability and Accountability Act.
Google LLC, AAA and Toyota Motor Corp. are among the more than 200 companies that Regal claims to supply. Customers of Five9 Inc.’s contact center platform gained access to Regal’s voice agents through an integration in August.
Regal is a venture capital-backed startup that has raised $83 million to date. This includes a $40 million round in October 2024.
Image: shelf
Support our mission to keep content open and free by interacting with theCUBE community. Join theCUBE Alumni Trust Networkwhere technology leaders connect, share information and create opportunities.
- Over 15 million viewers of theCUBE videosto spark conversations about AI, cloud, cybersecurity and more
- Over 11.4k theCUBE alumni — Connect with more than 11,400 technology and business leaders shaping the future through a unique, trusted network
Founded by tech visionaries John Furrier and Dave Vellante, SiliconANGLE Media has built a dynamic ecosystem of industry-leading digital media brands, reaching over 15 million elite tech professionals. Our new proprietary theCUBE AI Video Cloud is a game-changer in audience engagement, leveraging the theCUBEai.com neural network to help technology companies make data-driven decisions and stay at the forefront of the industry conversation.