Create with AI

Conversational AI from Google uses Natural Language Processing (NLP) to understand the meaning of words inside of phrases and the intent of your user.

Chatfuel Dialogflow Bot Stack

You can process a variety of user input with Dialogflow including text messages, quick reply buttons, images, and emoji.

Text All text input will hit your Default Answer in Chatfuel and save to a custom User Attribute called {{user input}}.
Quick Replies Save your quick reply buttons to {{user input}} and you can process button labels with Dialogflow.
Emoji Emoji are forms of text and will hit your Default Answer in Chatfuel and save to a custom User Attribute called {{user input}}
Stickers Facebook stickers include Messenger's blue thumbs up and this will hit your Default Answer in Chatfuel and save to a custom User Attribute called {{user input}}. A link will be passed to Janis and you can use a unique identifier contained in a URL to train Dialogflow to respond.

Dialogflow has a Default Message as well, referred to as a Default Fallback Intent, but your goal is to train Dialogflow to trigger Intents that produce the correct response for your user, and you'll find that Dialogflow presents a greater chance of producing the right response for your users.

Dialogflow training phrases

Phrases

A Dialogflow Intent includes training phrases. These are the things that users say to businesses on Messenger and help you understand the intent of the user when they send your bot a message.

Dialogflow training phrases

You can add your own phrases or start with our templates which include 1000's of phrases and you'll experience the benefits of AI immediately. Our free AI Starter Kit includes phrases for small talk so your bot can be more conversational and responsive to the most common phrases users say to Chatfuel bots.

Entities

Highlighted words inside of phrases are called Entities. These indicate that words can have different values, so the same phrase could have many different meanings because some words are variable. Some Entities are pre-built and are automatically triggered when you add phrases. Date, time, countries and cities are just some of the built-in Entities you can use. You can create your own entities too, like a menu for a restaurant. When you add phrases, entitities that are triggered create a paramaeter name and a parameter is the same thing as a User Attribute in Chatfuel.

Dialogflow Entities

If you create a User Attribute name in Chatfuel that matches the Parameter Name in Dialogflow, then the value you get from a user when a Dialogflow Intent is triggered is automatically saved in your matching User Attribute and included in your response to your user.

User Attributes

You can push these values into Chatfuel blocks and render messages, or set User Attribute filters in Go to block cards with Dialogflow values and trigger other Chatfuel blocks.

User Attributes

Responses

Every Dialogflow Intent has a response. You can add simple text responses in Dialogflow, or you can add a small snippet of JSON code to a Custom Payload response in Dialogflow so that you can redirect your response to a Chatfuel block. You simply include the exact name of the Chatfuel block in your Custom Payload.

Dialogflow custom payloads

In short, you can use Dialogflow to understand your users and then respond with Chatfuel blocks and use the data you capture from Dialogflow Intents to deliver rich and accurate responses with Chatfuel.


Putting Natural Language Processing To Work

  • Intents enable you to understand messages and their context and trigger responses. Think of an Intent as a Chatfuel block, but for AI.
  • Training phrases are messages your users will send your bot and which you'll use to train AI to learn how to respond.
  • Entities enable you to understand that a word inside of a phrase can have different values. Parameters are created when Entities are triggered in training phrases and a Parameter value can be automatically stored in a User Attribute in Chatfuel if it matches the Parameter name in Dialogflow.
  • Context enables your bot to know the context of a message you receive. You can add or remove a context in a block to enable or disable context in Dialogflow.
  • Events are alternatives to training phrases. For example, you could have your bot ask an open ended question for a survey and trigger a response from Dialogflow Intent with an Event.
  • Dialogflow supports multiple languages, and you can use a User Attribute to tell Dialogflow which language to respond with.