Both Dialogflow ES and Dialogflow CX support entities and they also behave similarly.

An entity represents a predefined categoy of objects and the basic idea is borrowed from the field of Natural Language Processing.

Named entity recognition (NER)—also called entity chunking or entity extraction—is a component of natural language processing (NLP) that identifies predefined categories of objects in a body of text.


In simpler language, you can say that entities are used to group proper nouns into similar categories or types.

For example, this is an entity of type planet with 9 entity “values” representing the 9 planet names.

The example above is a developer or user entity, which means it is defined by the developer (or person who creates the agent).

Dialogflow also has system entities. For example, it can identify the proper noun Miami as a system entity of type “city” automatically without the user specifying the entity name or supplying the entity values.

Also see:

System entity

Developer entity (also called User Entity)

Session entity