A Dialogflow agent is a virtual agent that handles concurrent conversations with your end-users. It is a natural language understanding module that understands the nuances of human language. Dialogflow translates end-user text or audio during a conversation to structured data that your apps and services can understand. You design and build a Dialogflow agent to handle the types of conversations required for your system.

A Dialogflow agent is similar to a human call center agent. You train them both to handle expected conversation scenarios, and your training does not need to be overly explicit.

Agents also serve as a top-level container for settings and data:

  • Agent settings for language options, machine learning settings, and other settings that control the behavior of your agent.
  • Intents to categorize end-user intentions for each conversation turn.
  • Entities to identify and extract specific data from end-user expressions.
  • Knowledge to parse documents (for example, FAQs) and find automated responses.
  • Integrations for applications that run on devices or services that directly handle end-user interactions for you (for example, Google Assistant).
  • Fulfillment to connect your service when using integrations.