Deprecated: Use inline suggestion, event based suggestion or Suggestion* API instead. See HumanAgentAssistantConfig.name for more details. Removal Date: 2020-09-01.
Retrieves suggestions for live agents.
This method should be used by human agent client software to fetch auto generated suggestions in real-time, while the conversation with an end user is in progress. The functionality is implemented in terms of the list pagination design pattern. The client app should use the nextPageToken field to fetch the next batch of suggestions. suggestions are sorted by createTime in descending order. To fetch latest suggestion, just set pageSize to 1. To fetch new suggestions without duplication, send request with filter create_time_epoch_microseconds > [first item's createTime of previous
request] and empty pageToken.
HTTP request
GET https://{endpoint}/v2beta1/{parent=projects/*/conversations/*/participants/*}/suggestions
Required. The name of the participant to fetch suggestions for. Format: projects/<Project ID>/locations/<Location
ID>/conversations/<Conversation ID>/participants/<Participant ID>.
Authorization requires the following IAM permission on the specified resource parent:
dialogflow.suggestions.list
Query parameters
Parameters
pageSize
integer
Optional. The maximum number of items to return in a single page. The default value is 100; the maximum value is 1000.
pageToken
string
Optional. The nextPageToken value returned from a previous list request.
filter
string
Optional. Filter on suggestions fields. Currently predicates on createTime and create_time_epoch_microseconds are supported. createTime only support milliseconds accuracy. E.g., create_time_epoch_microseconds > 1551790877964485 or createTime > "2017-01-15T01:30:15.01Z"
For more information about filtering, see API Filtering.
Required. The list of suggestions. There will be a maximum number of items returned based on the pageSize field in the request. suggestions is sorted by createTime in descending order.
nextPageToken
string
Optional. Token to retrieve the next page of results or empty if there are no more results in the list.
[[["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 2025-06-27 UTC."],[[["\u003cp\u003eThis API method retrieves real-time, auto-generated suggestions for live agents during conversations with end-users.\u003c/p\u003e\n"],["\u003cp\u003eThe API utilizes list pagination, using \u003ccode\u003enextPageToken\u003c/code\u003e to fetch subsequent batches of suggestions and allowing sorting by \u003ccode\u003ecreateTime\u003c/code\u003e in descending order.\u003c/p\u003e\n"],["\u003cp\u003eThe HTTP request is a \u003ccode\u003eGET\u003c/code\u003e operation targeting a specific participant's suggestions, with required path parameter \u003ccode\u003eparent\u003c/code\u003e in the format \u003ccode\u003eprojects/*/conversations/*/participants/*\u003c/code\u003e.\u003c/p\u003e\n"],["\u003cp\u003eOptional query parameters include \u003ccode\u003epageSize\u003c/code\u003e to limit results, \u003ccode\u003epageToken\u003c/code\u003e for pagination, and \u003ccode\u003efilter\u003c/code\u003e for filtering suggestions based on \u003ccode\u003ecreateTime\u003c/code\u003e or \u003ccode\u003ecreate_time_epoch_microseconds\u003c/code\u003e.\u003c/p\u003e\n"],["\u003cp\u003eThe response body includes a list of suggestions and an optional \u003ccode\u003enextPageToken\u003c/code\u003e to retrieve further suggestions.\u003c/p\u003e\n"]]],[],null,["# Method: projects.conversations.participants.suggestions.list\n\n- [HTTP request](#body.HTTP_TEMPLATE)\n- [Path parameters](#body.PATH_PARAMETERS)\n- [Query parameters](#body.QUERY_PARAMETERS)\n- [Request body](#body.request_body)\n- [Response body](#body.response_body)\n - [JSON representation](#body.ListSuggestionsResponse.SCHEMA_REPRESENTATION)\n- [Authorization scopes](#body.aspect)\n- [Try it!](#try-it)\n\n| This item is deprecated!\nDeprecated: Use inline suggestion, event based suggestion or Suggestion\\* API instead. See `HumanAgentAssistantConfig.name` for more details. Removal Date: 2020-09-01.\n\nRetrieves suggestions for live agents.\n\nThis method should be used by human agent client software to fetch auto generated suggestions in real-time, while the conversation with an end user is in progress. The functionality is implemented in terms of the [list pagination](https://cloud.google.com/apis/design/design_patterns#list_pagination) design pattern. The client app should use the `nextPageToken` field to fetch the next batch of suggestions. `suggestions` are sorted by `createTime` in descending order. To fetch latest suggestion, just set `pageSize` to 1. To fetch new suggestions without duplication, send request with filter `create_time_epoch_microseconds \u003e [first item's createTime of previous\nrequest]` and empty pageToken.\n\n### HTTP request\n\n`GET https://{endpoint}/v2beta1/{parent=projects/*/conversations/*/participants/*}/suggestions`\n\nWhere `{endpoint}` is one of the [supported service endpoints](/dialogflow/es/docs/reference/rest#rest_endpoints).\n\nThe URLs use [gRPC Transcoding](https://google.aip.dev/127) syntax.\n\n### Path parameters\n\n### Query parameters\n\n### Request body\n\nThe request body must be empty.\n\n### Response body\n\n| This item is deprecated!\nThe response message for [Participants.ListSuggestions](/dialogflow/es/docs/reference/rest/v2beta1/projects.conversations.participants.suggestions/list#google.cloud.dialogflow.v2beta1.Participants.ListSuggestions).\n\nIf successful, the response body contains data with the following structure:\n\n### Authorization scopes\n\nRequires one of the following OAuth scopes:\n\n- `https://www.googleapis.com/auth/cloud-platform`\n- `\n https://www.googleapis.com/auth/dialogflow`\n\nFor more information, see the [Authentication Overview](/docs/authentication#authorization-gcp)."]]