What is the CALM architecture and how does it benefit AI agents?
CALM (Conversational AI with Language Models) is Rasa's architecture that separates language understanding from execution. This design ensures fluent conversations while maintaining predictable and reliable results, even in complex enterprise environments, by allowing fine-tuning of LLMs for specific business needs.
Can Rasa AI agents be deployed in a private cloud or on-premises?
Yes, Rasa offers flexible deployment options, allowing AI agents to be deployed on-premises, in your private cloud infrastructure, or managed by partners, providing complete control over your data and environment.
How does Rasa ensure AI agents are cost-efficient at scale?
Rasa agents are designed to be cost-efficient by strategically using LLMs only when necessary. This approach optimizes resource consumption, ensuring that agents remain fast and flexible even across millions of conversations.
What is the difference between Rasa Pro and Rasa Studio?
Rasa Pro is a pro-code generative AI native conversational AI framework for developers, offering flexible tools for building, integrating, monitoring, and deploying AI Assistants. Rasa Studio is a no-code user interface built on top of Rasa Pro, designed for business users to build, analyze, and optimize AI Assistants with features like a flow builder and content management.
What kind of support is available for Rasa users?
Rasa offers community support through its forum for Free Developer Edition users. Enterprise customers receive Premium Support, which includes enhanced response times, 24/7/365 access to Customer Success Managers and Engineers, success planning, best practice guidance, and business reviews.
How does Rasa handle PII data and security for AI agents?
Rasa includes features for PII data management and enterprise security, such as dependency vulnerability protection and secrets management powered by Vault, to ensure that AI agents handle sensitive information securely and comply with data privacy requirements.