Regal Launches Goal Oriented Agents

Regal has introduced Goal Oriented Agents, a new capability for building artificial intelligence agents that can handle complex conversations without getting boxed in by rigid scripts.

With flexible agents operating from dual-agent architecture, the product unlocks more complex use cases, from Medicare enrollment, roadside assistance, mortgage qualification, and HIPAA-compliant medical intake. Instead of scripting the order of every question, users tell the agent what it needs to accomplish and the prerequisites to get there. It adaptively gathers the information it needs to reach that resolution.

Goal Oriented Agents' dual-model architecture includes the following:

• An actor, a smaller, fast model that drives the conversation, optimized for natural dialogue.
• A director that works in the background, checking progress against the goal requirements.

As soon as the caller finishes speaking, the actor and the director start working in parallel. The actor replies right away, while the director checks whether the goals for the current stage have been met. From there, it either suggests how the actor should guide the conversation or routes the call to a new stage with updated instructions for the actor.

Goals can be collected variables, like the caller's name, or tools, like scheduling a callback. Prerequisites can be data fields, like date of birth or location for a qualifying sale, or plain-language conditions, like the caller mentioned a death in the family. Once those goals and prerequisites are met, the agent can take an action or move on to the next goal within the node, bringing the conversation closer to resolution.

At the end of every turn, the director checks progress against both. When a caller shares extra context in a single answer, the director can check off several goals and prerequisites at once.