> [!WARNING]
>
> **Preview**
>
>
> This feature is
>
> subject to the "Pre-GA Offerings Terms" in the General Service Terms section of the
> [Service Specific
> Terms](https://docs.cloud.google.com/terms/service-terms#1).
>
> Pre-GA features are available "as is" and might have limited support.
>
> For more information, see the
> [launch stage descriptions](https://cloud.google.com/products/#product-launch-stages).

You can request real-time entity extraction during an Agent Assist
conversation. This feature automatically extracts data that matches any
Dialogflow [system entity](https://docs.cloud.google.com/dialogflow/docs/reference/system-entities)
in end-user expressions.

For example, if the end-user says "I want three tickets for Friday", "3" will
be extracted as a `@sys.number` entity, and "Friday" will be extracted as a
`@sys.date` entity. Agent Assist provides this data to your system during
the conversation, so you can display it on the human agent's user interface.
You can then use this data to provide the human agent with additional tools,
such as a button to schedule an event when a date is extracted.

## Enable real-time entity extraction

To enable real-time entity extraction, set the
`human_agent_assistant_config.message_analysis_config.enable_entity_extraction`
field to `true` when creating or updating a
[`ConversationProfile`](https://docs.cloud.google.com/dialogflow/es/docs/reference/rest/v2beta1/projects.conversationProfiles.md.txt).

## Get extracted data

When you call the `analyzeContent` or `streamingAnalyzeContent` method for the
[`Participant`](https://docs.cloud.google.com/dialogflow/es/docs/reference/rest/v2beta1/projects.conversations.participants.md.txt)
resource, the
`message.message_annotations.parts` field of the response contains the extracted
data.