Stay organized with collections
Save and categorize content based on your preferences.
This page describes how to view analytics for your recommendations
and search apps.
Analytics give you insight into the usage trends, search and recommendation
quality, and end-user engagement of your app. The AI Applications console
provides an interactive dashboard experience powered by Looker.
For media recommendations apps: Public preview. You can see
per-recommendation metrics based on user events. You can filter metrics by
date range and device type.
For custom search and media search apps: You can see per-search metrics
and per-search-session metrics based on search logs and user events. You can
filter metrics by date range, query, and device type.
For healthcare search apps: Public preview. You can see per-search metrics
based on search logs.
Metrics are refreshed about every six hours, so it can take several hours before
you can use the Analytics page after you create your app.
Data sources for analytics
This section describes the data sources for analytics depending on app type.
You must complete user events integration to be
able to see user event analytics.
Which user events you upload affect which analytics are generated.
Media recommendations apps require the following user events to view some
metrics:
View-item events. Required for click-through-rate.
Media-complete events. Required for completion rate per play and
completion rate per recommendation.
Media-play events. Required for recommendation media play count,
playthrough rate, completion rate per play, and average watch time per play.
Search apps require the following user events to view some metrics:
Search events. Required for click-through-rate.
View-item events. Required for click-through-rate.
The following information is also used for some analytics:
Impressions. You can provide impressions (item views or clicks) that are
attributable to Vertex AI Search by including the associated item
in UserEvent.Documents when ingesting user events. This information is
needed for attribution and to compute per-search metrics.
Attribution tokens. Attribution tokens are unique IDs generated by
Vertex AI Search and returned with each search request. Make sure
to include that attribution token as UserEvent.attributionToken with any
user events resulting from a search. This is needed to identify if a search
is served by the API. Only user events with a Google-generated attribution
token are used to compute metrics.
User agent. Include UserInfo.userAgent with user events so that
you can filter on user event metrics by device type.
Search logs
Search apps use search logs as data sources for some metrics.
Search logs are based on search requests. To allow AI Applications to
identify user sessions so that it can deliver per-session analytics and higher
quality search results, Google strongly recommends that you set the optional
field userPseudoId.
If there are not yet any search logs or user events, default values are shown
for all metrics.
View media recommendations analytics
Use the following instructions to view analytics for media recommendations.
In the Google Cloud console, go to the AI Applications page.
Click the name of the app that you want to view analytics for.
Click Analytics.
Click a tab to view that metric group:
Per Search. Metrics are grouped by searches. For healthcare search,
this is the only available metric group.
Per Session. Metrics are grouped by search sessions.
Compare. Baseline metrics are shown alongside metrics from a
comparison period. Select date ranges for the baseline metrics (an
earlier time range) and comparison metrics (a later time range). These
time ranges can't overlap.
To filter your metrics, specify the filters and then click
the Refresh button to apply them.
For media apps and for custom search apps, the following filters are
available:
Date range. Select a preset date range or, if available,
enter a custom date range.
Search query. Select a condition and search query value. You
can add multiple search query filters. Available for Per Search and
Compare metrics.
Device type. Select a device type that queries occurred on.
For healthcare search apps, the following filters are available:
Date range. Select a preset date range or, if available,
enter a custom date range. When you select a specific date for custom
date range, that date is the date when the search took place in the
UTC -08:00 time zone.
Search query. Select a condition and search query value. You
can add multiple search query filters.
User location. Select the location of the hospital, clinic, or the
healthcare service provider that was set in the search request. This
filter is available only if it was set in the search request.
User role. Select the job category of the user who sent the search
request. This
filter is available only if it was set in the search request.
User setting. Select the healthcare setting set in the search
request, such as inpatient, outpatient, or hybrid treatment. This
filter is available only if it was set in the search request.
Metrics definitions
The following tables describe how metrics are defined.
Media recommendations metrics
Metric name
Metric definition
Notes
Recommendation count
Total number of recommendations
Recommendation play count
Number of times that recommended media items were played
Recommendation click count
Number of times that recommended media items were clicked
Click-through rate
Count of recommendation clicks / recommendation count
Recommendation clicks are view-item events that can be attributed to a recommendation
Recommendation media complete count
Number of times that recommended media items were played to completion
Playthrough rate per recommendation
Number of times that recommended media items were played / recommendation count
Completion rate per play
Number of times that recommended media items were played to completion / number of times that media items were played
Average watch time per play
Time in seconds that recommended media items were played / number of times that recommended media items were played
Completion rate per recommendation
Number of times that media items were played to completion / recommendation count
Average watch time per recommendation
Time in seconds that recommended media items were watched / recommendation count
Media and custom search metrics
Metric name
Metrics Definition
Notes
Search count
Count of search events
Based on search logs.
No result rate
Count of search events
without results /
Search count
Based on search logs.
Click-through rate
(CTR) per search
Count of search clicks
/ Search count
Search clicks are
view-item events that
can be attributed to a
previous search event.
Based on user events.
Feedback like and
dislike count
Count of likes and
dislikes
A record of the
thumbs-up/thumbs-down
feedback responses
sent by the app's
users.
Feedback dislike
reasons breakdown
Percentage of the
dislike reasons
When a user dislikes a
generated answer, the
user can select
multiple reasons to
explain their dislike.
The percentage shows
how often each reason
was selected.
Search session
count
Count of search
sessions
A search session is a
user session
containing at least
one search event. A
user session, also
called a visit, is a
continuous set of user
events. When there are
30 minutes of
inactivity, the
session ends. Based on
search logs.
Page view per search
visit
Count of view-item
events in search
sessions / Search
session count
This metric includes
all page views in
search visits
regardless of whether
they can be attributed
to
Vertex AI Search.
Based on user events.
Bounce rate
Count of bounces in
search sessions /
Search session count
A search session
bounce is defined as a
session with a single
search, where the user
left after only making
one search. Based on
user events.
Healthcare search metrics
The following search metrics are available for healthcare search apps.
Metric name
Metrics Definition
Notes
Search count
Number of search events
No result count
Number of search events
without results
No result rate
per search
Number of search events
without results per
search
Patient count
Count of patient IDs for
which searches took
place
This is deduplicated
per search user but not
per patient. For
example, if user 1
searches for
patients A and B and
user 2 searches for only
patient B, then the
count is three.
Customer search
session count
Number of search
user-defined sessions
You can send a session
ID in your search.
For more information,
see
session.
A search session is a
user session
containing at least
one search event. A
user session, also
called a visit, is a
continuous set of user
events. When there are
30 minutes of
inactivity, the
session ends.
Turn off analytics
You can't turn off analytics for an existing app, but when you create an app you
can choose to create it with analytics turned off.
To create a search app that won't collect analytics data:
Follow the REST instructions in Create a search app, adding
the following to the curl command:
[[["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 2025-08-25 UTC."],[[["\u003cp\u003eThis page details how to access and interpret analytics for recommendations and search apps within the Vertex AI Agent Builder console.\u003c/p\u003e\n"],["\u003cp\u003eAnalytics dashboards, powered by Looker, provide insights into app usage, search and recommendation quality, and user engagement, with data refreshed approximately every six hours.\u003c/p\u003e\n"],["\u003cp\u003eSpecific metrics and filtering options vary depending on whether the app is for media recommendations, generic search, or healthcare search, all of which support filtering by date range and device type.\u003c/p\u003e\n"],["\u003cp\u003eUser events, such as view-item, media-complete, and search events, are critical for generating certain metrics, and for search apps, search logs are used as a data source for some metrics.\u003c/p\u003e\n"],["\u003cp\u003eWhile analytics are enabled by default, new search apps can be created without analytics by setting \u003ccode\u003e"disableAnalytics": true\u003c/code\u003e in the REST API configuration.\u003c/p\u003e\n"]]],[],null,["# View analytics\n\nThis page describes how to view analytics for your recommendations\nand search apps.\n\nAnalytics give you insight into the usage trends, search and recommendation\nquality, and end-user engagement of your app. The AI Applications console\nprovides an interactive dashboard experience powered by Looker.\n\n- **For media recommendations apps**: Public preview. You can see per-recommendation metrics based on user events. You can filter metrics by date range and device type.\n- **For custom search and media search apps**: You can see per-search metrics and per-search-session metrics based on search logs and user events. You can filter metrics by date range, query, and device type.\n- **For healthcare search apps**: Public preview. You can see per-search metrics based on search logs.\n\nMetrics are refreshed about every six hours, so it can take several hours before\nyou can use the **Analytics** page after you create your app.\n\nData sources for analytics\n--------------------------\n\nThis section describes the data sources for analytics depending on app type.\n\nYou must complete user events integration to be\nable to see user event analytics.\n\nWhich user events you upload affect which analytics are generated.\n\nMedia recommendations apps require the following user events to view some\nmetrics:\n\n- **View-item events.** Required for click-through-rate.\n- **Media-complete events.** Required for completion rate per play and completion rate per recommendation.\n- **Media-play events.** Required for recommendation media play count, playthrough rate, completion rate per play, and average watch time per play.\n\nSearch apps require the following user events to view some metrics:\n\n- **Search events.** Required for click-through-rate.\n- **View-item events.** Required for click-through-rate.\n\nThe following information is also used for some analytics:\n\n- **Impressions** . You can provide impressions (item views or clicks) that are attributable to Vertex AI Search by including the associated item in `UserEvent.Documents` when ingesting user events. This information is needed for attribution and to compute per-search metrics.\n- **Attribution tokens** . Attribution tokens are unique IDs generated by Vertex AI Search and returned with each search request. Make sure to include that attribution token as `UserEvent.attributionToken` with any user events resulting from a search. This is needed to identify if a search is served by the API. Only user events with a Google-generated attribution token are used to compute metrics.\n- **User agent** . Include `UserInfo.userAgent` with user events so that you can filter on user event metrics by device type.\n\n### Search logs\n\nSearch apps use search logs as data sources for some metrics.\n\nSearch logs are based on search requests. To allow AI Applications to\nidentify user sessions so that it can deliver per-session analytics and higher\nquality search results, Google strongly recommends that you set the optional\nfield [`userPseudoId`](/generative-ai-app-builder/docs/reference/rest/v1/projects.locations.collections.engines.servingConfigs/search#body.request_body.FIELDS.user_pseudo_id).\n\nIf there are not yet any search logs or user events, default values are shown\nfor all metrics.\n\nView media recommendations analytics\n------------------------------------\n\n| **Note:** Media recommendations analytics are in Public preview.\n\nUse the following instructions to view analytics for media recommendations.\n\n1. In the Google Cloud console, go to the **AI Applications** page.\n\n [AI Applications](https://console.cloud.google.com/gen-app-builder/start)\n2. Click the name of the app that you want to view analytics for.\n\n3. Click **Analytics**.\n\n4. To filter your metrics, specify any of the following filters and then click\n the **Refresh** button to apply them:\n\n - **Date range**. Select a preset date range or, if available, enter a custom date range.\n - **Device type**. Select a device type that queries occurred on.\n\nView search analytics\n---------------------\n\n| **Notes:**\n|\n| - For data stores in US and EU multi-regions, viewing search analytics is in Public preview.\n| - Because AI Applications for healthcare search provides search services only in the US multi-region (\\`us\\`), analytics for healthcare search are in Public preview.\n| - Search analytics are GA for global data stores.\n| - By default, metrics from the widget don't appear on the **Analytics** page. To view widget metrics, contact your Google account team and ask to be added to the allowlist.\n\nUse the following instructions to view analytics for search apps.\n\n1. In the Google Cloud console, go to the **AI Applications** page.\n\n [AI Applications](https://console.cloud.google.com/gen-app-builder/start)\n2. Click the name of the app that you want to view analytics for.\n\n3. Click **Analytics**.\n\n4. Click a tab to view that metric group:\n\n - **Per Search**. Metrics are grouped by searches. For healthcare search, this is the only available metric group.\n - **Per Session**. Metrics are grouped by search sessions.\n - **Compare**. Baseline metrics are shown alongside metrics from a comparison period. Select date ranges for the baseline metrics (an earlier time range) and comparison metrics (a later time range). These time ranges can't overlap.\n5. To filter your metrics, specify the filters and then click\n the **Refresh** button to apply them.\n\n For media apps and for custom search apps, the following filters are\n available:\n - **Date range**. Select a preset date range or, if available, enter a custom date range.\n - **Search query** . Select a condition and search query value. You can add multiple search query filters. Available for **Per Search** and **Compare** metrics.\n - **Device type**. Select a device type that queries occurred on.\n\n For healthcare search apps, the following filters are available:\n - **Date range**. Select a preset date range or, if available, enter a custom date range. When you select a specific date for custom date range, that date is the date when the search took place in the UTC -08:00 time zone.\n - **Search query**. Select a condition and search query value. You can add multiple search query filters.\n - **User location**. Select the location of the hospital, clinic, or the healthcare service provider that was set in the search request. This filter is available only if it was set in the search request.\n - **User role**. Select the job category of the user who sent the search request. This filter is available only if it was set in the search request.\n - **User setting**. Select the healthcare setting set in the search request, such as inpatient, outpatient, or hybrid treatment. This filter is available only if it was set in the search request.\n\nMetrics definitions\n-------------------\n\nThe following tables describe how metrics are defined.\n\n### Media recommendations metrics\n\n### Media and custom search metrics\n\n### Healthcare search metrics\n\nThe following search metrics are available for healthcare search apps.\n\nTurn off analytics\n------------------\n\nYou can't turn off analytics for an existing app, but when you create an app you\ncan choose to create it with analytics turned off.\n\nTo create a search app that won't collect analytics data:\n\n1. Follow the REST instructions in [Create a search app](/generative-ai-app-builder/docs/create-engine-es), adding\n the following to the curl command:\n\n \"disableAnalytics\": true\n\n #### Example command\n\n ```\n curl -X POST \\\n -H \"Authorization: Bearer $(gcloud auth print-access-token)\" \\\n -H \"Content-Type: application/json\" \\\n -H \"X-Goog-User-Project: my-project-123\" \\\n \"https://discoveryengine.googleapis.com/v1/projects/my-project-123/locations/global/collections/default_collection/engines?engineId=my-app\" \\\n -d '{\n \"displayName\": \"App without analytics\",\n \"dataStoreIds\": [\"my-data-store\"],\n \"solutionType\": \"SOLUTION_TYPE_SEARCH\",\n \"searchEngineConfig\": {\n \"searchTier\": \"SEARCH_TIER_ENTERPRISE\",\n \"searchAddOns\": [\"SEARCH_ADD_ON_LLM\"]\n },\n \"disableAnalytics\": true\n }'\n\n \n ```\n\n\n This command creates an app that won't collect search analytics data."]]