Stay organized with collections
Save and categorize content based on your preferences.
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 match an end-user input to any other intents.
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 match an end-user input to any other intents.
This intent is not matched if an audio input doesn't contain any transcribed
speech.
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.
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.
Negative examples
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.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-08-07 UTC."],[[["\u003cp\u003eTwo intents, the default welcome intent and the default fallback intent, are automatically created when you create an agent.\u003c/p\u003e\n"],["\u003cp\u003eThe default welcome intent is triggered at the start of a conversation to greet the user, and it can be matched either by a greeting training phrase or a welcome event from an integration.\u003c/p\u003e\n"],["\u003cp\u003eThe default fallback intent activates when the agent fails to match the user's input with any other defined intents, and it comes pre-configured with responses that can be customized.\u003c/p\u003e\n"],["\u003cp\u003eYou can customize the responses of both default intents, ensuring they effectively guide the user, and even add negative examples to the fallback intent.\u003c/p\u003e\n"],["\u003cp\u003eYou can create additional fallback intents and use contexts to customize the fallback responses.\u003c/p\u003e\n"]]],[],null,["# Default intents\n\nTwo intents are created automatically when you create an agent:\n\n- **Default welcome intent**: matched when an end-user begins a conversation with your agent.\n- **Default fallback intent**: matched when your agent doesn't match an end-user input to any other intents.\n\n| **Note:** You can delete the default intents, but it is normally best to keep them and customize them for your agent.\n\nDefault welcome intent\n----------------------\n\nThe default welcome intent is matched\nwhen an end-user begins a conversation with your agent.\nIt should return a response that lets end-users know\nwhat your agent does or what end-users can say to begin a conversation.\nYou should customize the pre-populated intent responses for your agent.\n\nThe default welcome intent is matched in one of two ways:\n\n- One of its training phrases are matched, which are pre-populated with common greetings, like \"hello\".\n- This intent has a [welcome event](/dialogflow/docs/events-platform#welcome_events) attached to it, which is triggered when the end-user begins a conversation with your agent via a supported [integration](/dialogflow/docs/integrations).\n\n| **Note:** The default welcome intent includes various greeting training phrases in all languages, however these training phrases are not used for invocation by Google Assistant. See the Google Assistant [invocation](https://developers.google.com/assistant/discovery) documentation for more information.\n\nDefault fallback intent\n-----------------------\n\nThe default fallback intent is matched\nwhen your agent doesn't match an end-user input to any other intents.\n\nThis intent is not matched if an audio input doesn't contain any transcribed\nspeech.\n\nThis intent is automatically configured\nwith a variety of static text responses,\nlike \"I didn't get that. Can you say it again?\".\n\nYou can customize fallback intents\nby changing the pre-populated text responses\nor by adding negative examples.\n\nYou can also create additional fallback intents:\n\n1. Go to the [Dialogflow ES console](https://dialogflow.cloud.google.com).\n2. Select an agent.\n3. Select **Intents** in the left sidebar menu.\n4. Click the option *more_vert* button at the top of the intents page.\n5. Select **Create Fallback Intent**.\n\n### Fallback intent responses\n\nYou can change the pre-populated text responses,\nbut they should communicate to the end-user\nthat their input was not recognized.\n| **Note:** You can have multiple fallback intents with [contexts](/dialogflow/docs/contexts-overview) to customize fallback responses.\n\n### Negative examples\n\nYou can add training phrases to fallback intents\nthat act as *negative examples*.\nThere may be cases where end-user expressions\nhave a slight resemblance to your training phrases,\nbut you do not want these expressions to match any normal intents.\n\nFor example, a room booking service may have a training phrase like\n\"I'd like to book a room\".\nIf the end-user wants to purchase a book about rooms, they may say\n\"I'd like to buy a book about rooms.\"\nTo ensure that the end-user expression does not match your intent,\nyou can add that phrase as a negative example."]]