Google recently announced the testing of the beta-version of its natural language platform – Dialogflow CX. While the earlier verison enabled customers with intuitive omnichannel conversational AI, Dialogflow CX is an advanced development suite for creating AI-based agents for enterprise-level projects and improving customer experience.
It will allow enterprises to create conversational AI applications including chatbots, voicebots, IVR bots and more. With a visual bot-building platform, it has collaboration and versioning tools optimised for enterprise scale and complexity. It brings features such as interactive flow visualisations, omnichannel implementation, handling complex customer questions, and more.
The company stated that Dialogflow CX provides a new way of designing agents, taking a state machine approach to agent design. This gives user a clear and explicit control over a conversation, a better end-user experience, and a better development workflow.
It also said that the service previously named Dialogflow is now called Dialogflow ES, and the term Dialogflow is now an umbrella term used to describe both the Dialogflow ES and Dialogflow CX services.
Google has offered Dialogflow as a tool for building text and voice-based AI agents usable for mobile apps, websites, and Google Assistant Actions. It allows user to speak to the virtual agent naturally. It then processes the information and responds appropriately based on the programming. Dialogflow CX adds another tier of ability to its existing virtual agents allowing to handle multiple conversation topics at once. It will also have better ability to respond to a user with follow-up questions.
Dialogflow is still in beta and lacks many of the standard version’s features. For instance, agents can only speak English and do not offer integrations or option to import data. The company however, is likely to add these features before the complete product is released.
Earlier this year Google had released beta of a Dialogflow Mega Agent that combines multiple Dialogflow agents, called sub-agents, into a single agent, called a mega agent. It made a single virtual agent flexible enough to handle a wide variety of situations.
