Regal Voice Inc. said on October 27, 2026 that it added Goal Oriented Agents to its platform. Businesses build agents from goal nodes, each listing the goals to meet by the end of that node and any prerequisites that must come first, and prerequisites can be written as plain-language conditions.
Each call runs two models. The actor is a smaller, faster dialogue model that replies right away, while the director checks goal progress after every turn and can move the call to a new stage with fresh instructions for the actor. In Regal's sample auto insurance claim, one caller's first message filled three fields at once, so the agent moved straight to asking for his name.
Regal names Medicare enrollment, roadside assistance, mortgage qualification and HIPAA-compliant medical intake as possible uses. The company says it serves more than 200 enterprises, including Google, AAA and Toyota, and that Five9 customers gained access to its voice agents through an integration in August. Regal has raised $83 million to date.
Why it matters if you build agents
Developers building voice agents for intake or qualification calls can express required data points as goals and prerequisites instead of hand-coding branching flows. This trades a single open prompt for explicit stage checks, so teams should test how reliably the director marks items as collected. The article gives no performance figures, so results on real call flows will need to be measured.
Get stories like this every weekday
One short email with the day's agent tooling news.