Two intents are created automatically when you create an agent:
- Default welcome intent: matched when an end-user begins a conversation with your agent.
- Default fallback intent: matched when your agent doesn't recognize an end-user expression.
Default welcome intent
The default welcome intent is matched when an end-user begins a conversation with your agent. It should return a response that lets end-users know what your agent does or what end-users can say to begin a conversation. You should customize the pre-populated intent responses for your agent.
The default welcome intent is matched in one of two ways:
- One of its training phrases are matched, which are pre-populated with common greetings, like "hello".
- This intent has a welcome event attached to it, which is triggered when the end-user begins a conversation with your agent via a supported integration.
Default fallback intent
The default fallback intent is matched when your agent doesn't recognize an end-user expression. This intent is automatically configured with a variety of static text responses, like "I didn't get that. Can you say it again?".
You can customize fallback intents by changing the pre-populated text responses or by adding negative examples.
You can also create additional fallback intents:
- Go to the Dialogflow ES Console.
- Select an agent.
- Select Intents in the left sidebar menu.
- Click the option more_vert button at the top of the intents page.
- Select Create Fallback Intent.
Fallback intent responses
You can change the pre-populated text responses, but they should communicate to the end-user that their input was not recognized.
You can add training phrases to fallback intents that act as negative examples. There may be cases where end-user expressions have a slight resemblance to your training phrases, but you do not want these expressions to match any normal intents.
For example, a room booking service may have a training phrase like "I'd like to book a room". If the end-user wants to purchase a book about rooms, they may say "I'd like to buy a book about rooms." To ensure that the end-user expression does not match your intent, you can add that phrase as a negative example.