AI News Feed
Market watch
Products & Applications

Regal launches Goal Oriented Agents with actor and director models on every call

Regal Voice launched Goal Oriented Agents, a voice AI system that puts an actor model and a director model on each call to track goals, handle complex intake and move conversations between stages.

The new agents are intended to address a problem Regal says appears in calls such as auto insurance claims, where a person reporting an accident may explain what happened, where and who was involved all at once. Agents built on conditional logic often ask again for details the caller has already provided so that each field can be filled. Building the entire agent on a single prompt keeps the conversation open, but in Regal’s view leaves business processes only loosely followed.

Goal Oriented Agents put two models on each call. Regal calls them an actor and a director, and both begin work as soon as the caller stops talking. The actor, a smaller and faster model tuned for dialogue, replies immediately. Running behind it, the director checks whether the goals for the current stage have been met and can move the call to a new stage with fresh instructions for the actor.

Businesses build the agents from goal nodes, each listing the goals to be met by the end of the node and any prerequisites that must come first. Booking a callback can count as one goal. A prerequisite is something the agent must establish before it can act, such as the caller’s date of birth. Regal said those can also be written as plain-language conditions, for example that the caller mentioned a death in the family.

The director reviews progress after every turn, so one answer can satisfy several items at once. In Regal’s sample auto insurance claim, a caller named Dan describes vehicle damage, photo evidence and injuries in his first message. All three are marked as collected, and the agent goes straight to his name. Once it has that, the director sees that location and policy number are still missing, so the actor’s next question is where he is.

Regal said complex intake and qualification calls are among the strongest uses it has seen for the agents. The company named Medicare enrollment, roadside assistance and mortgage qualification as uses the design opens up. Medical intake that complies with the Health Insurance Portability and Accountability Act is another.

Google LLC, AAA and Toyota Motor Corp. are among the more than 200 enterprises Regal says it serves. 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, including a $40 million round in October 2024.

Editor's Summary

Regal Voice has launched Goal Oriented Agents, which use an actor model for immediate replies and a director model to track goals and stage transitions on each call. The design is aimed at complex intake and qualification calls, with Medicare enrollment, roadside assistance and mortgage qualification cited as target uses. Regal, which has raised $83 million, counts Google, AAA and Toyota among more than 200 enterprise customers.