01 Dialogflow CX vs Dialogflow ES Feature Comparison

Dialogflow ES vs Dialogflow CX

Dialogflow CX is much more powerful than Dialogflow ES if you would like to design multi-turn conversation flows. This is possible because Dialogflow CX has been designed from the ground up to design your conversation flow as a state machine. In fact, I think the word “transition” in the phrase Intent Transition Route is borrowed from the idea of state transitions, which is common terminology when describing state machines.

For example, suppose you want to use slot filling. Slot filling is extremely unpredictable in Dialogflow ES, but Dialogflow CX provides some important features to get around this unpredictability because of its state-machine oriented design.

Feature Comparison

In the table below I provide feature-by-feature comparison between Dialogflow ES and Dialogflow CX.

FeatureDialogflow ESDialogflow CX
Conversation DesignUse input and output contextsUse pages, routes and flows
Collect a list of inputs from userUse follow up intents or mimic follow up intentsUse pages and intent transition routes
Store user inputUse contextsUse built-in session params
Slot fillingBasic and unpredictablePowerful and robust
Supports explicit contextsYesNo
WebhooksOne endpoint per agentOne endpoint per transition route is possible
Support for list entityYesYes
Support for composite entityYesYes
Supports Regex entityYesYes
Agent VersioningBasicPowerful
Free tierGenerous free tierNo, but provides free trial credits
Built in integrationsMany 1-click integrations are supported, including many third party appsLimited support for 1-click integrations
Supports Test casesNoYes
Support for system functionsNoYes
Supports conditional logic inside consoleNoYes
Exception handling when conversation goes off trackHard, needs a good understanding of the CTFS frameworkVery robust, possibly best among all chatbot frameworks
Supports Knowledge BaseYesNo (use route groups instead)
Build a large bot with a lot of intentsUse the Mega Agent feature (less robust)Use Flows (more robust)
Note: This is my old website and is in maintenance mode. I am publishing new articles only on my new website. 

If you are not sure where to start on my new website, I recommend the following article:

Is Dialogflow still relevant in the era of Large Language Models?

Leave a Reply