Regal debuts Goal Oriented Agents with actor-director AI per call

Regal's launch targets a specific failure mode in voice agents: conditional-logic designs that ask callers for details they already gave, and single-prompt designs that keep conversation open but leave business processes loosely followed. Goal Oriented Agents address this by splitting the work. The actor, a smaller and faster dialogue model, replies immediately, while the director reviews progress after every turn. In Regal's sample auto insurance claim, caller Dan describes vehicle damage, photo evidence and injuries in his first message; all three are marked collected and the agent moves straight to his name.

Businesses build agents from goal nodes listing goals to be met by the end of the node and any prerequisites, such as a date of birth, that must come first. Regal said those conditions can be written in plain language, for example “the caller mentioned a death in the family.” That matters for complex intake and qualification calls, where Regal named Medicare enrollment, roadside assistance, mortgage qualification and HIPAA-compliant medical intake as uses the design opens up.

Regal is a venture capital-backed startup that has raised $83 million to date, including a $40 million round in October 2024. It says it serves more than 200 enterprises, among them Google LLC, AAA and Toyota Motor Corp., and customers of Five9 Inc.'s contact center platform gained access to its voice agents through an integration in August.