Multimodal AI Agents That Can Plan, Reason And Explain

New patent underscores‘s unique neuro-symbolic AI approach to create hallucination-free conversations between humans and AI agents

BRIDGEWATER, N.J., March 19, 2024 /PRNewswire/ —, the leading provider of multimodal neuro-symbolic Conversational AI solutions for visionaries, today announced it has expanded its portfolio of intellectual capital with the grant of a new patent comprising a system and method for cooperative plan-based utterance-guided multimodal dialogue. AI Virtual Assistants, AI Avatars, and AI Voice Agents created with Openstream’s Eva™ (Enterprise Virtual Assistant) platform can understand end-user intentions by leveraging multimodal inputs and context to infer user’s plans to dynamically generate human-like dialogue in real-time across any channel without a script or hallucinations.

“When people engage a brand’s agent, they expect an empathetic and knowledgeable agent that understands them regardless of modality, channel, or language,” says David Stark,’s CMO. Stark continues “AI agents must generate and understand context-specific dialogue using all end-user inputs in real-time to seamlessly engage them in unscripted conversations that feel natural and help them to achieve their goals. Without this, brand perception and long-term relationships are at risk.”

The sophistication, intelligence, and potential for the variety of conversations that multimodal AI virtual assistants can engage in, leaps forward with this patented approach. AI agents created with Eva can engage in complex, multimodal, multi-turn, multi-obstacle conversations continually informed by context. Businesses can improve levels of customer satisfaction in comparison to simple chatbots or scripted agents by providing AI agents that understand and generate real-time dialogue with their customers, prospects, and employees across any channel or language 24/7/365.

“This patented technology shows how advanced our approach for dialogue management is, and how it can handle conversations that are hard for many other contemporary solutions,” says Magnus Revang,’s CPO. Revang continues: “Our system goes far beyond intent-slot, and frame-based systems – to reason and plan using very complex constraints and domain knowledge.”

End-users do not have to endure the frustrating conversations with chatbots & virtual assistants that employ intent-slot models where they are forced to adapt their communication style, goals, and expectations to what the system can handle. This patent ensures that collaborative plan-based multimodal agents can be used to help improve the quality of customer interactions and customer satisfaction while enhancing long-term customer retention for any enterprise. serves enterprises across the industries that seek to improve the quality of their relationships leveraging neuro-symbolic AI to compete more effectively and efficiently. Eva’s Conversational AI platform addresses the unique needs of enterprises by including features for Explainability, Reasoning, Trust, Data Governance, and Privacy Protection to provide them with solid foundations for growth while reducing risk.

About enables enterprises to engage in meaningful and fluid conversations with their audiences across modalities, channels, and languages with its visionary multimodal, plan-based Conversational AI, Eva (Enterprise Virtual Assistant). The platform is finely tuned by world-class AI experts to orchestrate the latest AI approaches and tools to deliver the best solutions possible for their end-users and businesses. The company is headquartered in Bridgewater, NJ, and offers its solutions and expertise to visionary enterprises worldwide.

Learn more about Eva and Enterprise-Class Conversational AI solutions from® at

Media Contact:

(908) 685-5844