On 1st September, Google announced the launch of DialogFlow CX (Customer Experience), a new way to design a chatbot that is suitable for large or very complex virtual agents. DialogFlow CX is not a new NLU, it’s a platform that is aimed at building artificial intelligence agents for enterprise-level projects at a larger and more complex scale than the standard variety.
What happened to the old version?
The older version of Dialogflow has been branded to Dialogflow ES (short for Essentials). The Standard Edition is now called DialogFlow Trail edition and Dialogflow Enterprise Edition is no longer used for the paid edition. Dialogflow Plus Edition and Dialogflow Essentials Edition have been merged to one Dialogflow Essentials (ES) Edition. DialogFlow ES is still used for developing smaller and less complex bots.
So, basically the term Dialogflow is now an umbrella term used to describe both the Dialogflow ES and Dialogflow CX services.
In this article, let me summarize the key enhancements in Dialogflow CX compared to ES.
DialogFlow CX
According to Google, “Dialogflow CX provides a new way of designing agents, taking a state machine approach to agent design. This gives you clear and explicit control over a conversation, a better end-user experience, and a better development workflow.”
Let’s look at some of the differences between the versions:
Intents: The ES and CX version uses intents, however in the CX version it has been simplified to make it reusable. And intent is not used together with context to control conversation flow. Instead, it works with pages to navigate/route through the conversations
Context to Page: In the ES version, the context was used to determine the control of the conversation flow. Dialogflow CX completely eliminates the concept of the input and output contexts in favor of the Visual State Machine. The Page is to manage the states of a conversation session. It is used to collect information from the end-user that is related to the state designed on the page. Similar to ES edition, a page has the following elements:
· Entry Dialog — defines the agent’s response when a page is active
· Parameters — used to collect critical data points for fulfillment
· Routes — Two types: Intent requirement & Conditional requirements which are used to control the flow.
Session level parameters: When you collect user input, you need some way to keep track of what information they provided in prior steps (conversation turns). By default, Dialogflow ES encouraged people to use a large context lifespan for this purpose, which caused problems with managing the conversation flow. In DialogFlow CX, Session level parameters are now built-in automatically.
Source: https://chatbotslife.com/dialogflow-es-and-cx-b32b450b2d50?source=rss—-a49517e4c30b—4