# Generative BI with Quick Sight Generative BI with Quick Sight **Note** Powered by Amazon Bedrock: Amazon Q in Quick is built on Amazon Bedrock and includes [automated abuse detection](https://docs.aws.amazon.com//bedrock/latest/userguide/abuse-detection.html) implemented in Amazon Bedrock to enforce safety, security, and the responsible use of AI. With Amazon Quick chat, you can utilize the Generative BI authoring experience, create executive summaries of your data, ask and answer questions of data, and generate data stories. To access all Quick Sight Generative BI features that are relevant to your task, choose the sparkle icon at the top right of any Quick page. In the pane that opens, the chat displays all content that is available based on the context of the task that you are performing. For example, if you're working in an Analysis, you can build a calculation, edit visuals, set up Q&A, or ask questions about your data. If you're working in a Dashboard, you can build a data story, generate an executive summary, or ask questions about the dashboard. **Note** Generative BI features are not available in all AWS regions. To see a list of regions that Generative BI features are available in, see [Supported AWS Regions for Amazon Q in Quick](regions.md#regions-aqs) Use the following topics to learn more about Generative BI. **Topics** + [ # Get started with Generative BI ](generative-bi-get-started.md) + [ # Augmenting Amazon Quick Sight insights with Amazon Q Business ](generative-bi-q-business.md) + [ # The Generative BI authoring experience ](generative-bi-author-experience.md) + [ # Creating executive summaries ](gen-bi-executive-summaries.md) + [ # Authoring Q&A ](gen-bi-author-q-and-a.md) + [ # Manage topic permissions through dashboards in Amazon Quick Sight ](gen-bi-manage-topic-permissions.md) + [ # Turn on the Dashboard Q&A experience in Amazon Quick Sight ](dashboard-qa.md) + [ # Q&A null support ](gen-bi-q-and-a-null-support.md) + [ # Improve Q&A accuracy with custom instructions ](gen-bi-improve-qa-accuracy-with-custom-instructions.md) + [ # Asking and answering questions of data with Generative BI ](gen-bi-data-q-and-a.md) + [ # Opting out of Generative BI ](generative-bi-opt-out.md) + [ # Working with Amazon Quick Sight Topics ](topics.md) + [ # Working with data stories in Amazon Quick Sight ](working-with-stories.md) + [ # Working with scenarios in Amazon Quick Sight ](scenarios.md) # Get started with Generative BI Get started To get started with Quick Sight Generative BI capabilities, upgrade your account's users to Admin Pro, Author Pro, or Reader Pro roles. Pro roles grant users access to all Generative BI capabilities that are relevant to the role that's assigned to the user. Pro users can share generative Q&A topics with another user. To understand which Generative BI capabilities are available to the different user roles in Quick, see the table below. To understand how subscription names map to user roles, see [Understanding Amazon Quick subscriptions and roles](https://docs.aws.amazon.com/quicksight/latest/user/user-types.html#subscription-role-mapping). **Note** Non-Pro Authors and Readers can still access Generative Q&A topics if an Author Pro or Admin Pro user shares the topic with them. Non-Pro Authors and Readers can also access data stories if a Reader Pro, Author Pro, or Admin Pro shares one with them. | Feature name | Feature description | Reader | Author | Admin | Reader Pro | Author Pro | Admin Pro | | --- | --- | --- | --- | --- | --- | --- | --- | | [Creating a data story with Generative BI](working-with-stories-create.md) | Build data stories that explain your data with visuals, insights, and ideas to help improve your business. | ![\[alt text not found\]](http://docs.aws.amazon.com/quick/latest/userguide/images/negative_icon.svg) No | ![\[alt text not found\]](http://docs.aws.amazon.com/quick/latest/userguide/images/negative_icon.svg) No | ![\[alt text not found\]](http://docs.aws.amazon.com/quick/latest/userguide/images/negative_icon.svg) No | ![\[alt text not found\]](http://docs.aws.amazon.com/quick/latest/userguide/images/success_icon.svg) Yes | ![\[alt text not found\]](http://docs.aws.amazon.com/quick/latest/userguide/images/success_icon.svg) Yes | ![\[alt text not found\]](http://docs.aws.amazon.com/quick/latest/userguide/images/success_icon.svg) Yes | | [Viewing a generated data story in Amazon Quick Sight](working-with-stories-view.md) | View narrative data stories that are shared with you. | ![\[alt text not found\]](http://docs.aws.amazon.com/quick/latest/userguide/images/success_icon.svg) Yes\$1 | ![\[alt text not found\]](http://docs.aws.amazon.com/quick/latest/userguide/images/success_icon.svg) Yes\$1 | ![\[alt text not found\]](http://docs.aws.amazon.com/quick/latest/userguide/images/success_icon.svg) Yes\$1 | ![\[alt text not found\]](http://docs.aws.amazon.com/quick/latest/userguide/images/success_icon.svg) Yes | ![\[alt text not found\]](http://docs.aws.amazon.com/quick/latest/userguide/images/success_icon.svg) Yes | ![\[alt text not found\]](http://docs.aws.amazon.com/quick/latest/userguide/images/success_icon.svg) Yes | | [Authoring Q&A](gen-bi-author-q-and-a.md) | Create and refine topics that utilize Generative Q&A for Quick Sight dashboards. | ![\[alt text not found\]](http://docs.aws.amazon.com/quick/latest/userguide/images/negative_icon.svg) No | ![\[alt text not found\]](http://docs.aws.amazon.com/quick/latest/userguide/images/negative_icon.svg) No | ![\[alt text not found\]](http://docs.aws.amazon.com/quick/latest/userguide/images/negative_icon.svg) No | ![\[alt text not found\]](http://docs.aws.amazon.com/quick/latest/userguide/images/negative_icon.svg) No | ![\[alt text not found\]](http://docs.aws.amazon.com/quick/latest/userguide/images/success_icon.svg) Yes | ![\[alt text not found\]](http://docs.aws.amazon.com/quick/latest/userguide/images/success_icon.svg) Yes | | [Asking and answering questions of data with Generative BI](gen-bi-data-q-and-a.md) | Ask questions about data to accelerate data driven decisions with multi-visual answers. | ![\[alt text not found\]](http://docs.aws.amazon.com/quick/latest/userguide/images/success_icon.svg) Yes\$1 | ![\[alt text not found\]](http://docs.aws.amazon.com/quick/latest/userguide/images/success_icon.svg) Yes\$1 | ![\[alt text not found\]](http://docs.aws.amazon.com/quick/latest/userguide/images/success_icon.svg) Yes\$1 | ![\[alt text not found\]](http://docs.aws.amazon.com/quick/latest/userguide/images/success_icon.svg) Yes | ![\[alt text not found\]](http://docs.aws.amazon.com/quick/latest/userguide/images/success_icon.svg) Yes | ![\[alt text not found\]](http://docs.aws.amazon.com/quick/latest/userguide/images/success_icon.svg) Yes | | [Creating executive summaries](gen-bi-executive-summaries.md) | Get an executive summary of key insights from a Quick Sight dashboard. | ![\[alt text not found\]](http://docs.aws.amazon.com/quick/latest/userguide/images/negative_icon.svg) No | ![\[alt text not found\]](http://docs.aws.amazon.com/quick/latest/userguide/images/negative_icon.svg) No | ![\[alt text not found\]](http://docs.aws.amazon.com/quick/latest/userguide/images/negative_icon.svg) No | ![\[alt text not found\]](http://docs.aws.amazon.com/quick/latest/userguide/images/success_icon.svg) Yes | ![\[alt text not found\]](http://docs.aws.amazon.com/quick/latest/userguide/images/success_icon.svg) Yes | ![\[alt text not found\]](http://docs.aws.amazon.com/quick/latest/userguide/images/success_icon.svg) Yes | | [The Generative BI authoring experience](generative-bi-author-experience.md) | Create an analysis to build visuals, calculations, and refine existing visuals with natural language. | ![\[alt text not found\]](http://docs.aws.amazon.com/quick/latest/userguide/images/negative_icon.svg) No | ![\[alt text not found\]](http://docs.aws.amazon.com/quick/latest/userguide/images/negative_icon.svg) No | ![\[alt text not found\]](http://docs.aws.amazon.com/quick/latest/userguide/images/negative_icon.svg) No | ![\[alt text not found\]](http://docs.aws.amazon.com/quick/latest/userguide/images/negative_icon.svg) No | ![\[alt text not found\]](http://docs.aws.amazon.com/quick/latest/userguide/images/success_icon.svg) Yes | ![\[alt text not found\]](http://docs.aws.amazon.com/quick/latest/userguide/images/success_icon.svg) Yes | \$1Non-pro roles in accounts that were created on or after April 30, 2024 can access Q&A topics that are shared with them. If your Quick account was created before April 30, 2024 and you want to opt-in to this new feature, contct your AWS account team. Any Quick administrator can upgrade a user to a Pro role with the following procedure. **To upgrade a user to a Pro role** 1. Open the [Quick console](https://quicksight.aws.amazon.com/). 1. Choose the user icon at the top right, and then choose **Manage Quick**. 1. Choose **Manage users** to open the **Manage Users** page. 1. To change the role of an existing user, locate that user on the **Manage Users** table and choose the role that you want to grant them from the **Role** dropdown. For more information about managing Quick users, see [Managing user access inside Amazon Quick](managing-users.md). # Augmenting Amazon Quick Sight insights with Amazon Q Business Amazon Quick account admins can connect their Quick account to Amazon Q Business to augment insights with unstructured data sources. [Amazon Q Business](https://aws.amazon.com//q/business/) is a generative AI assistant that helps your team work smarter. It can answer questions, provide summaries, generate content, and securely complete tasks based on the information in your enterprise systems. When an Quick account is integrated with Amazon Q Business, users can now leverage this vast repository of organizational knowledge alongside their structured data analytics. This integration allows for more comprehensive and context-rich insights, as it combines quantitative data from Quick with qualitative information from various business documents and applications. For more information about connecting your Amazon Q Business account with Quick, see [Creating an Quick-integrated application](https://docs.aws.amazon.com/amazonq/latest/qbusiness-ug/create-application-quicksight.html). Use the following topics to configure an Amazon Q Business application in Quick. **Topics** + [ ## Considerations ](#generative-bi-q-business-considerations) + [ # Configuring an Amazon Q Business application in Amazon Quick Sight ](generative-bi-q-business-configure.md) + [ # Connect a Quick account to an existing Amazon Q Business application ](generative-bi-q-business-link-existing-account.md) + [ # Disconnect an Amazon Q Business application from an Amazon Quick account ](generative-bi-q-business-delete-connection.md) ## Considerations The following limitations apply to the Amazon Q Business application. + Quick and Amazon Q Business must exist in the same AWS account. Cross account calls are not supported. + Quick and Amazon Q Business accounts need to exist in the same AWS Region. Cross Region calls are not supported. For a list of all supported Quick Regions, see [Supported AWS Regions for Amazon Q in Quick](regions.md#regions-aqs). For a list of all supported Amazon Q Business Regions, see [Service quotas for Amazon Q Business](https://docs.aws.amazon.com/amazonq/latest/qbusiness-ug/quotas-regions.html). If your Quick account exists in more than one Region, you can connect one Amazon Q Business application from each Region to the Quick account. For example, if your Quick account exists in US East (N. Virginia) and US West (Oregon), one Amazon Q Business application located in US East (N. Virginia) and one Amazon Q Business application located in US West (Oregon) can be connected to the Quick account. + Quick and Amazon Q Business accounts that are integrated need to use the same identity methods. For example, if a Quick account uses IAM Identity Center for identity management, the Amazon Q Business account that it is integrating with must also use IAM Identity Center for identity management. + Email addresses that are associated with Quick users and groups are used to perform authorization checks in Amazon Q Business. # Configuring an Amazon Q Business application in Amazon Quick Sight Create a new Amazon Q Business application in Quick Sight Use the following procedure to connect an Amazon Quick account with Amazon Q Business 1. Open the [Quick console](https://quicksight.aws.amazon.com/). 1. Choose the user icon at the top right, and then choose **Manage Quick**. 1. Choose **Security & permissions**. 1. On the **Quick access to AWS services** page, choose the **Amazon Q Business application** checkbox. 1. On the **Create an Amazon Q Business connection to unstructured data** popup that appears, choose the Quick Region that you want your connection to be in. 1. Choose **Done**. 1. When you choose **Done**, your Amazon Q Business account is created and you are redirected to a new tab that shows the **Applications** page of the Amazon Q Business console. 1. For **Applications**, choose the Amazon Q Business connection that you created in Quick. 1. The **Application details** page of your connection opens. Choose the **Index** tab, and then choose **Select index**. 1. In the popup that appears, choose the **Index provisioning** option that you want to use, and then choose **Confirm**. For more information about indexes in Amazon Q Business, see [Creating a retriever for an Amazon Q Business application](https://docs.aws.amazon.com/amazonq/latest/qbusiness-ug/select-retriever.html). 1. After you choose an index, set up a data source connection. To set up a data source connection, choose the **Data sources** section of the **Enhancements** menu in the left side pane. 1. Choose **Add data source**. 1. Choose the data source that you want to add. The data source that you choose determines the steps that are required to configure the data source connection. For more infotmation about adding a data source to an Amazon Q Business account, see [Connecting Amazon Q Business data sources](https://docs.aws.amazon.com/amazonq/latest/qbusiness-ug/supported-connectors.html). When you finish setting up the data source configuration, choose **Add data source**. After you choose an index, a retriever, and a data source for your Amazon Q Business account, your connection to Amazon Q Business is complete and you can return to the Quick console. # Connect a Quick account to an existing Amazon Q Business application Connect Quick to an existing Amazon Q Business application If you already have an Amazon Q Business application that uses the same identity management and exists in the same Region as your Quick account, use the following procedure to link the existing Amazon Q Business account to Quick. 1. Open the [Quick console](https://quicksight.aws.amazon.com/). 1. Choose the user icon at the top right, and then choose **Manage Quick**. 1. Choose **Security & permissions**. 1. On the **Quick access to AWS services** page, choose the **Amazon Q Business application** checkbox. 1. On the **Create an Amazon Q Business connection to unstructured data** popup that appears, choose the Quick Region that you want your connection to be in. 1. Choose your existing Amazon Q Business application from the dropdown. **Note** Your Amazon Q Business application does not appear if the application exists in a different Region than your Quick account or if the application uses a different identity management option than your Quick account. After you choose your Amazon Q Business application from the dropdown, the connection between Quick and Amazon Q Business is configured. # Disconnect an Amazon Q Business application from an Amazon Quick account Disconnect an Amazon Q Business application from Quick Quick account admins can use the following procedure to disconnect an Amazon Q Business application from a Quick account. 1. Open the [Quick console](https://quicksight.aws.amazon.com/). 1. Choose the user icon at the top right, and then choose **Manage Quick**. 1. Choose **Security & permissions**. 1. On the **Quick access to AWS services** page, choose **SELECT APPLICATION**. 1. Perform one of the following options: 1. To disconnect a single Amazon Q Business application from a Quick account, navigate to the application that you want to remove, open the dropdown, and choose **NONE**. 1. To disconnect all Amazon Q Business applications from a Quick account, uncheck the **Amazon Q Business application** checkbox. When you disconnect an Amazon Q Business application from a Quick account, the Amazon Q Business application that you created for Quick is not deleted. The application, index, retriever, and any unstructured data source connections that you configured remain in your Amazon Q Business account. # The Generative BI authoring experience Authoring experience With Quick chat, authors can use new Generative BI capabilities to build calculated fields and to build and refine visuals. You can also generate complete multi-sheet analyses from natural language prompts. For more information, see [Generating an analysis with natural language prompts](generating-an-analysis.md). Use the following topics to learn more about the Generative BI authoring experience. **Topics** + [ # Build visuals with Generative BI ](generative-bi-build-visuals.md) + [ # Build calculations with Generative BI ](generative-bi-build-calculations.md) + [ # Refine visuals with generative BI ](generative-bi-refine-visual.md) # Build visuals with Generative BI Build visuals Quick authors can use the **Build a visual** button to build a custom visual that's generated from author input. The author's input uses natural language to describe the desired outcome for the new visual. You can enter a custom description, or you can choose from a list of generated suggestions that Amazon Q has generated for the topic that's attached to the analysis. The following image shows a custom visual that's created with the **Build a visual** menu. **To build a visual with Generative BI** 1. Navigate to the analysis that you want to work in and choose **Ask to build a visual**. 1. In the **Build a visual** panel that appears, perform the following steps. 1. Describe the data that you want to visualize. You can enter a custom description, or you can choose from the **Suggested** questions that are generated based on the analysis' data. When you describe the data that you want to visualize, you can phrase it as a question, or you can use conversational phrases or filters. For example, you can enter "How many people signed up for a free trial last month?" or "Free trial sign ups by month." Both statements generate a visual that shows the number of free trial sign-ups by month. You can also get responses to vague language or keyword style requests. Suggested questions can include a mix of artificial intelligence (AI) generated questions and human verified questions. Human verified questions appear with a check mark next to the suggestion. 1. Choose **Build**. 1. Review the visual that generates. To refine the data presented in the visual, enter a new description into the **Build** bar, and then choose **Build**. Use the forward and back arrows to review the changes made to the visual without losing any progress. 1. When you're satisfied with the visual, choose **ADD TO ANALYSIS**. # Build calculations with Generative BI Build calculations With Generative BI, you can use natural language prompts to create calculated fields in Amazon Quick Sight, as shown in the following image. For more information about calculated fields in analyses, see [Adding calculated fields](adding-a-calculated-field-analysis.md). ![\[Adding a calculated field with the Build tool.\]](http://docs.aws.amazon.com/quick/latest/userguide/images/gen-bi-build-calculation-1.png) **To build a calculated field with Generative BI** 1. Navigate to the analysis that you want to work in and choose **Data** from the toolbar at the top of the page. Then choose **Add calculated field**. 1. In the calculation editor that appears, choose **Build**. 1. Describe the calculation outcome that you want to achieve. For example, "year over year percent change in daily sales." 1. Choose **BUILD**. 1. Review the expression that's returned, and then choose **Insert** to add it to the expression editor. You can also choose the **Copy** icon to copy the expression to your clipboard. To delete the expression and start over, choose the **Delete** icon next to the expression. 1. When you're finished, close the editor. After you add a calculation to the expression editor, you must name the calculation before you can save it. # Refine visuals with generative BI Refine visuals Quick authors can also use natural language prompts to edit visuals in an analysis, as shown in the following visual. Authors can use this functionality to edit visuals without performing manual tasks in the Quick UI. Authors can only use Generative BI to perform formatting tasks that are currently supported in Quick. The following types of edit are supported: + Change a visual's type. + Show or hide axis titles, axis labels, or data labels. + Show, hide, or change the title of a chart. + Change axis and table column names. + Add fields or field wells to a visual. + Remove fields from a visual. + Change the aggregation of an axis. + Show or hide legends and grid lines. + Show or hide data zoom. + Add fields or field wells to a visual. + Change or remove a visual's sort controls. + Update the conditional formatting of a visual's colors, color gradients, background color, or text color. + Change the time granularity of a visual. + Adjust axis scaling and range, as well as maximum and minimum values. + Change font sizes of titles and subtitles. + Show, hide, and adjust data labels. + Adjust column formatting (change between number, percent, date, and currency). **To edit a visual with Generative BI** 1. Navigate to the visual that you want to edit, and then choose **Edit with Q**. 1. Describe the task that you want performed, and then choose **APPLY**. 1. Review the visual changes. If you're satisfied with the generated changes, close the **Edit visual** modal. To undo the changes, choose **Undo** and enter a new prompt. # Creating executive summaries Executive summaries With Quick chat, you can leverage large language models (LLMs) to generate executive summaries of dashboards. Executive summaries are based on Quick Sight's suggested insights for a dashboard. Executive summaries help readers find key insights at a glance without the need to pinpoint specific data from a dashboard's visuals. To turn on executive summaries for a dashboard, turn on **Allow executive summary** on the **Publish a dashboard** modal. For more information about how readers can interact with executive summaries, see [Generate an executive summary of an Amazon Quick Sight dashboard](use-executive-summaries.md). Executive summaries work best when an analysis has multiple suggested insights. To see a list of all suggested insights for an analysis, navigate to the analysis that you want to work in, and then open the **Insights** pane. # Authoring Q&A ## Converting to the Generative Q&A experience If you have existing topics, you can easily convert these to leverage our new generative capabilities. Navigate to a topic, and then choose **Convert** next to the topic name. You will then be prompted to **Duplicate & Convert Topic** in a dialog box. We duplicate your topic for you so that the conversion to our beta experience does not impact your end users. Once you are satisfied with topic performance in the new experience, you can unshare the original topic and share the new one. ## Named entities Named entities are one of the most important components of topic curation. The information contained in named entities — specifically, the ordering of fields and their ranking — is what makes it possible to present contextual, multi-visual answers in response to even vague questions. Authors can find named entities by navigating to a topic, choosing the **Data** tab, and then choosing the **Named Entities**. From here, authors can preview or edit existing named entities, and create new ones. Authors can configure the following facets of named entities: 1. **Fields**: Choose a dataset, and then choose which fields from that dataset to include. This defines the scope of data that will be considered when using this named entity to answer enduser questions. 1. **Field Rank and Presentation**: The relative rank of the dimensions and measures in a named entity determines how those fields are used when generating contextual, multi-visual answers. Note in the following demo that adjusting the relative rank of **Profit** so that it is higher than **Sales** leads to different data being displayed. By default, the order of fields in the table visual is the same as the field rank. However, you can control these two individually by turning off **Sync table view with field ranking**. 1. **Show / Hide in Presentation**: Fields that are included in named entities can simultaneously be hidden from the tabular presentation of the named entity, while still providing additional context in other components of the answer. ## Measure aggregations Authors have fine-grained control over aggregated measures in topics. Across Quick Sight, measures are defaulted to `SUM`,unless they have custom aggregations defined in a calculated expression. To change this, navigate to the measure in the list of data fields, and specify a different default aggregation. You can also disallow aggregations, which will prevent them from being applied even if a user specifically asks for them. Lastly, you can specify that a measure is non-additive. This is useful for pre-computed metrics, such as percentages, which should not be re-combined in any way. Doing so will force `MEDIAN` or `AVG` depending on your use case. # Manage topic permissions through dashboards in Amazon Quick Sight Manage topic permissions through dashboards Quick enables Authors to manage permissions for dashboards and their linked topics from a single location. When sharing dashboards with Q&A enabled, Authors can control topic viewer access directly from a dashboard's sharing preferences, eliminating the need to manage permissions in multiple locations. **To enable Q&A on a dashboard with a linked topic:** 1. Open the [Quick console](https://quicksight.aws.amazon.com/). 1. Open the analysis of the dashboard with Q&A enabled and topic linked that you want to publish. 1. Choose **Publish**. 1. Check the **Allow data Q&A** check box. 1. Choose **MANAGE Q&A** and select **Use a linked topic for Build visual and Q&A**. 1. Select the desired linked topic from the dropdown menu. 1. Choose **APPLY CHANGES**, then choose **Publish dashboard**. **To conveniently manage topic access from a dashboard:** 1. Open the [Quick console](https://quicksight.aws.amazon.com/). 1. Open the dashboard with a linked topic that you are a co-owner of. 1. Select the share icon and choose **Share dashboard**. 1. In the row of your selected user, flip on/off the **Share as "topic viewer"** toggle to grant/revoke viewer access to the linked topic. 1. In the row of your selected shared folder, flip on/off the **Add topic to folder** toggle to add/remove the linked topic to/from the shared folder. **To share the dashboard and its linked topic to all users and groups:** 1. Open the [Quick console](https://quicksight.aws.amazon.com/). 1. Open the dashboard with a linked topic that you are a co-owner of. 1. Select the share icon and choose **Share dashboard**. 1. On the bottom-left of the panel, under **Auto-share linked topic for**, flip the **All dashboard users and groups** toggle on. This will grant viewer access to the linked topic when the dashboared is shared. Flip the toggle off to cancel this behavior. After the dashboard with a linked topic has been shared, users will immediately be able to ask questions about their data. Navigate to **Ask a question about ** at the top of the dashboard to start asking questions. # Turn on the Dashboard Q&A experience in Amazon Quick Sight Quick allows any Author to enable Q&A directly from their dashboards in one click without the need to create a Topic in Quick Sight. To do this, publish your dashboard and check the **Allow data Q&A** checkbox from the dashboard publishing menu. When you turn on dashboard Q&A, you can choose which datasets to use for dashboard Q&A to ensure that your end users get the answers they need. Dashboard Q&A queries all rows and columns in the included datasets - beyond what is visible in the dashboard. To protect sensitive or confidential data, enable [row-level security (RLS)](row-level-security.md) and/or [column-level security (CLS)](restrict-access-to-a-data-set-using-column-level-security.md). The following table compares feature availability between dashboard Q&A and topic Q&A. | Q&A feature | Dashboard Q&A | Topic Q&A | | --- | --- | --- | | Allows users in all roles to ask and answer questions of data | ![\[alt text not found\]](http://docs.aws.amazon.com/quick/latest/userguide/images/success_icon.svg) Yes | ![\[alt text not found\]](http://docs.aws.amazon.com/quick/latest/userguide/images/success_icon.svg) Yes | | Allows author and admin roles to enable data Q&A on dashboards | ![\[alt text not found\]](http://docs.aws.amazon.com/quick/latest/userguide/images/success_icon.svg) Yes | ![\[alt text not found\]](http://docs.aws.amazon.com/quick/latest/userguide/images/negative_icon.svg) No (Pro users only) | | Suported in Quick console embedding | ![\[alt text not found\]](http://docs.aws.amazon.com/quick/latest/userguide/images/negative_icon.svg) No | ![\[alt text not found\]](http://docs.aws.amazon.com/quick/latest/userguide/images/success_icon.svg) Yes | | Ability to add reviewed answers | ![\[alt text not found\]](http://docs.aws.amazon.com/quick/latest/userguide/images/negative_icon.svg) No | ![\[alt text not found\]](http://docs.aws.amazon.com/quick/latest/userguide/images/success_icon.svg) Yes | | Ability to customize Q&A-specific metadata | ![\[alt text not found\]](http://docs.aws.amazon.com/quick/latest/userguide/images/negative_icon.svg) No | ![\[alt text not found\]](http://docs.aws.amazon.com/quick/latest/userguide/images/success_icon.svg) Yes | | Ability to support autocomplete for data values | ![\[alt text not found\]](http://docs.aws.amazon.com/quick/latest/userguide/images/negative_icon.svg) No | ![\[alt text not found\]](http://docs.aws.amazon.com/quick/latest/userguide/images/success_icon.svg) Yes | Use the procedure below to enable dashboard Q&A on a Quick Sight dashboard. **To enable dashboard Q&A on a dashboard** 1. Open the [Quick console](https://quicksight.aws.amazon.com/). 1. Open the analysis that the dashboard that you want to publish with Q&A enabled. 1. Choose **Publish**. 1. Check the **Allow data Q&A** check box. 1. (Optional) Choose **MANAGE Q&A** to choose which datasets you want to include in the dashboard Q&A experience. By default, all datasets that are used by the dashboard are included. 1. Choose **APPLY CHANGES**, and then choose **Publish dashboard**. After you publish a dashboard with the dashboard Q&A experience enabled, users can ask questions about their data with the **Ask a question about this dashboard** input at the top of the dashboard. Quick allows any user to ask questions on dashboards that have dashboard Q&A enabled. However, dashboard Q&A is a feature that incurs the associated enablement fee. Quick admins can disable this feature at the account level at any time. Use the following procedure to disable dashboard Q&A across an entire Quick account. 1. Open the [Quick console](https://quicksight.aws.amazon.com/). 1. Choose the user icon in the top right, and then choose **Manage Quick**. 1. Choose **Security & permissions**. 1. Navigate to the Amazon Q section, and then choose **Manage**. 1. Toggle **Manage Dashboard Q&A** off. When you toggle **Manage Dashboard Q&A** off, dashboard Q&A is removed from any dashboards that have dashboard Q&A enabled. If your Quick account does not have Pro users or topics, this action stops the Amazon Q enablement fee from billing your Quick account. This setting does not impact Pro users or existing topics in Quick. For more information about opting out of Generative BI, see [Opting out of Generative BI](generative-bi-opt-out.md). # Q&A null support Amazon Quick Sight Q&A has comprehensive support for null value handling, enabling users to create more sophisticated analyses and answer complex business questions. This functionality allows for precise filtering of null values, intuitive queries about missing data, and dynamic chart interactions. ## Add a filter to include or exclude null values **To add a filter to include or exclude null values** 1. Open the [Quick console](https://quicksight.aws.amazon.com/). 1. Choose **Topics** and then open the topic you want to add a filter to. 1. Choose the **Data** tab. 1. Under **Data Fields**, choose **Add filter**. 1. On the **Filter configuration** page that opens, do the following: 1. For **Name**, enter a name for the filter. 1. For **Dataset**, choose a dataset that you want to apply the filter to. 1. For **Field**, choose the field that you want to filter for. 1. For **Null Option**, choose one of the dropdown options: + **No null option selected** - No option is selected to filter nulls. + **Include nulls only** - Filter for only nulls on the field selected. + **Exclude nulls only** - Filter for only non nulls on the field selected. 1. (Optional) To specify when the filter is applied, choose **Apply the filter anytime the dataset is used**, and then choose one of the following: 1. **Apply always** - Filter is applied whenever a column from the specified dataset is linked to a question. 1. **Apply always, unless a question results in an explicit filter from the dataset** - Filter is applied whenever a column from the specified dataset is linked to a question, unless the question contains its own explicit filter for the same field. 1. Choose **Save**. The filter is added to the list of fields in the topic. You can edit the description for it or adjust it when the filter is applied. ## Ask a question on null values You can use Q&A to directly ask questions about null values, such as: + What is the total sales amount for records where the segment is null? + Display accounts without assigned representatives. + List projects with no completion date. + Show inventory items without category assignments. + What percentage of total orders have non null values in the license field by segment? + Which orders do not have a customer assigned? ## Manage null values in visualizations After generating visualizations through the Q&A bar, you can interact with the charts using various null value actions, including focusing only on null values or excluding null values. These chart actions help you analyze and filter your data dynamically based on null value presence. Choose either **Focus only on null** or **Exclude null** to appropriately filter the results. ![\[alt text not found\]](http://docs.aws.amazon.com/quick/latest/userguide/images/focus-on-null.png) ## Refine query interpretations for null value handling Once the visualizations are generated based on your query, you can adjust how null values are handled. 1. Locate the **Interpreted as** section below your query. 1. Select the field you wish to modify. 1. From the dropdown menu, choose **Null Options** to adjust null value handling. ![\[alt text not found\]](http://docs.aws.amazon.com/quick/latest/userguide/images/interpreted-as.png) For categorical fields, empty values are not the same as null values. To convert empty values into nulls: 1. Open the [Quick console](https://quicksight.aws.amazon.com/). 1. Choose **Topics** and then open the topic you want to add a filter to. 1. Choose the **Data** tab. 1. Choose **Add calculated field**. 1. Enter a name for the **Add name** field. 1. Choose a categorical field and enter an expression to convert empty values to null values: `ifelse({Segment}="",NULL,{Segment})`. 1. Choose **Save**. # Improve Q&A accuracy with custom instructions Custom Instructions enables Authors to curate Amazon Q's responses to questions by adding domain-specific knowledge that can’t be captured through a topic’s metadata settings, such as synonyms or semantic types. By providing these metadata descriptions or custom instructions, Authors can guide Amazon Q to align its responses with distinct definitions, preferences, and expert knowledge—ensuring more accurate, relevant, and tailored answers that are better suited for their business needs. Use the following table to understand when and how to apply different types of metadata to improve Q&A answer accuracy. Each metadata type plays a unique role in clarifying context, resolving ambiguity, and ensuring that answers are aligned with business rules or domain-specific terminology. | Metadata Type | When to Use | How it Improves Answer Accuracy | | --- | --- | --- | | Field-Level Description | When the Q&A system needs to understand ambiguous or domain-specific column names (for example, `DTC Spend`). | Clarifies field semantics so the model can answer more precisely (for example, interpreting `DTC Spend` as Direct-to-Consumer marketing expense). | | Topic-Level Description | When users may ask broad or ambiguous questions and Amazon Q needs more context about the topic's overall purpose (for example, sales performance vs. clinical trial data). | Helps disambiguate general terms and steer answers toward the right domain (for example, sales vs. marketing). | | Dataset Description | When users have access to multiple datasets and the Q&A system needs to identify which one best fits the question. | Enables dataset selection logic by providing context about each dataset's purpose and content. | | Topic-Level Custom Instructions | When a topic has specific business rules, timeframes, or definitions (for example, fiscal year ≢ calendar year). | Applies custom logic or definitions (for example, defining Q1 as August-October) to tailor answers appropriately. | ## Adding field-level descriptions **To add field-level descriptions:** 1. Open the [Quick console](https://quicksight.aws.amazon.com/). 1. Choose **Topics** and then open the topic you want to add descriptions for. 1. From the topic details page, select the **Data** tab then choose the **Data Fields** sub-tab. 1. Add a description to improve answer accuracy for each included field. This is especially important for field names that contain bespoke corporate knowledge to understand. If you have multiple date fields, for example, clear descriptions can help Amazon Q distinguish between them and choose the most relevant one based on the user’s question. In the sample below, an Author added descriptions for **Solution Create** and **Topic Create**, which enables Amazon Q to more accurately select the appropriate date field in context. ![\[solution create description\]](http://docs.aws.amazon.com/quick/latest/userguide/images/solution_create.png) ![\[topic create description\]](http://docs.aws.amazon.com/quick/latest/userguide/images/topic_create.png) ## Adding topic-level descriptions **To add topic-level descriptions:** 1. Open the [Quick console](https://quicksight.aws.amazon.com/). 1. Choose **Topics** and then open the topic you want to add descriptions for. 1. From the topic details page, select the **Summary** tab. 1. Under **Topic Details**, add a description to provide more context about the topic's overall purpose. ## Adding dataset descriptions **To add dataset descriptions:** 1. Open the [Quick console](https://quicksight.aws.amazon.com/). 1. Choose **Topics** and then open the topic you want to add descriptions for. 1. From the topic details page, select the **Data** tab then choose the **Datasets** sub-tab. 1. Add a description to help improve dataset selection logic. ## Adding topic-level custom instructions **To add custom instructions:** 1. Open the [Quick console](https://quicksight.aws.amazon.com/). 1. Choose **Topics** and then open the topic you want to add descriptions for. 1. From the topics details page, select the **Custom Instructions** tab. 1. Add topic-level guidance to help the chat better understand the context, terminology, or intent that is specific to the selected topic. This can include disambiguation tips, field relationships, definitions for terms that can’t be captured in a calculated field or topic filter, or instructions for customizing relative date ranges. ## Best practices for writing custom instructions **Match cell values precisely** + Use the exact cell value from the database, including casing and formatting. + If the value is ambiguous, reference its source column to clarify. Examples: + Instead of: "*AMZ are Amazon customers*" Use: "*AMZ are 'Amazon.com, Inc.' customers*" + Instead of: "*ETPs are enterprise customers*" Use: "*ETPs are customers from the enterprise Segment*" **Be specific and quantitative** Avoid vague language—be clear about filters, thresholds, and source columns. Example: + Instead of: "*Filter large customers when talking about sales*" Use: "*Filter customers where Annual Revenue > \$11M when talking about sales*" **Use formatting for clarity, not function** Spacing and line breaks do not affect model behavior, but help authors read and maintain instructions more easily. **Understand what custom instructions cannot do** Custom instructions improve the understanding of your business context, but they do not add new capabilities. These instructions will not: + Change chart type selections + Perform calculations or fill nulls + Create new fields + Control formatting, colors, or legends + Alter the narrative or number/type of visuals ## Adding field-level descriptions in data preparation for dashboard-based Q&A In addition to Topic-based descriptions, you can create field-level definitions to enhance [Dashboard Q&A](dashboard-qa.md) functionality. Adding specific definitions to individual fields during the data preparation phase improves the answer accuracy when users ask questions about particular dashboard elements. **To add field-level descriptions for dashboard-based Q&A:** 1. Open the [Quick console](https://quicksight.aws.amazon.com/). 1. Choose **Data**, open a dataset that you have access to, and select **EDIT DATASET**. 1. For each relevant field, choose the three-dot menu and select **Edit name & description**. 1. Add a description to enhance answers for dashboard-related questions. 1. Choose **Apply** to save your changes. # Asking and answering questions of data with Generative BI **Note** To view the multi-visual experience, the topic author must do the following: add named entities, and convert an existing topic to use generative capabilities or create a new generative topic. For more information, see [Authoring Q&A](gen-bi-author-q-and-a.md). Accelerate data-driven decisions with humanistic Q&A that includes: + AI-generated narrative that highlights key insights + Multi-visual answer that provides the answer to your question along with supporting visuals to add valuable context + Home page for every topic with AI-generated and author-reviewed suggested questions and automated data previews to see what data you can ask about Choose the sparkle icon at the top right. Once you open your topic, there is a home page with a list of suggested questions and **What’s in your topic** to see what data you can ask about. When there are multiple dates available, choose **more...** to view them. For example, in this Student Enrollment Trends topic, there is data available for enrollment data spanning from 2018 to 2023, but there is also student Date of Birth (DOB) data ranging from 1973 to 2005. Choose a suggested question or type your own question to get started. By hovering over a sentence in the AI-generated narrative, you can clearly identify the source visualization and verify the values. Each visualization is interactive and can be added to your pinboard. You can get answers to a variety of questions from vague to precise. If you don’t have a precise question in mind, you can ask a vague question that is only one word or a short phrase, like *“sales”* or *“top students."* You can include additional filter criteria with these vague questions like *“top students last semester."* Question examples include: + Entity name: *“Order Details"* + **Note** You can find the entities from the topic home page and in the **What’s in *topic*** tab at the top of the list. + Field name: “Segment” + Field values: “Acme Inc.,” “Washington DC” + Vague (or implicit) filters: “best account managers," “bottom products” For precise questions that are supported, see this table of question types: [Types of questions supported by Q](https://docs.aws.amazon.com/quicksight/latest/user/quicksight-q-ask.html#quicksight-q-ask-types). Examples include “product with largest WoW growth %” or “forecast sales for APAC customers by quarter.” It covers a range of filters, like top/bottom, relative and absolute date filters, period-to-date and period-over-period, and more. It also supports analytical questions, like percent of total, or “why did sales drop in October 2023?" **Tip** To help you form questions, think *Who*, *What*, *Where*, *When* and *Why*. Unpacking your answer: + **Interpreted as:** – This is how Amazon Q interpreted your question. It will map your words to the underlying data so you can verify that you were correctly understood. If not, adjust your question or leave feedback for your author. + **AI-generated narrative:** – A summary of the visuals that highlights key insights. If your Quick account is connected to an Amazon Q application, you may receive additional insights from unstructured data sources under **Insights from Q Business**. You can see the unstructured sources that are used in the **Sources** collabsible. For more information about connecting a Quick account to a Amazon Q Business application, see [Augmenting Amazon Quick Sight insights with Amazon Q Business](generative-bi-q-business.md). + **Visuals:** – Visuals consist of: center visual that directly answers the question, supporting visual on the right that provides context, relevant KPIs, and a details table at the bottom. **Note** If the field is not included in a named entity, then it will display as a single visual. + **Did you mean:** – When there are multiple interpretations to your question, it will display a list of alternate answers that you can select to align with your intended question. + In the following example, the question "top customers” can be interpreted in several ways, including by “Total Sales,” “Total Profit,” or “number of customers." ![\[alt text not found\]](http://docs.aws.amazon.com/quick/latest/userguide/images/top-customers.png) Other tips + To re-size the panel, drag the left side. + Add important visuals to your pinboard for quick access. View your pinboard from the top of the Amazon Q pane. + Provide feedback for your topic author to see and make improvements. # Opting out of Generative BI Quick accounts are charged if Generative BI is active in the account. Generative BI is considered active if your account uses any of the following capabilities: + Pro users + Topics + Dashboard and visual indexing + Dashboard Q&A To avoid being charged for Generative BI by completely deactivating it, perform the following steps. **Warning** Opting out of Generative BI will disable AI-powered features and stop related charges. This process involves: Removing or changing Pro user roles to standard roles Deleting all topics in your account Disabling dashboard indexing and Q&A features **Before proceeding:** Review the steps carefully and ensure you understand which features will be disabled. **To opt out of Generative BI** 1. Ensure there are no Pro users or user groups mapped to Pro roles in the account by performing the following steps: + To update or remove Pro users using APIs: + If you use Quick identity (with or without IAM federation): 1. Find users that have Pro roles using the [ListUsers](https://docs.aws.amazon.com/quicksight/latest/APIReference/API_ListUsers.html) API. 1. Either change the users' roles using the [UpdateUser](https://docs.aws.amazon.com/quicksight/latest/APIReference/API_UpdateUser.html) API, or remove the users from the account using the [DeleteUser](https://docs.aws.amazon.com/quicksight/latest/APIReference/API_DeleteUser.html) API. + If you use IAM Identity Center or Microsoft Active Directory: 1. Find group of users mapped to Pro roles using the [ListRoleMemberships](https://docs.aws.amazon.com/quicksight/latest/APIReference/API_ListRoleMemberships.html) API. 1. Create new user groups with the same users, but mapped to different roles, using the [CreateRoleMemberships](https://docs.aws.amazon.com/quicksight/latest/APIReference/API_CreateRoleMemberships.html) API. 1. Delete the previous user groups mapped to Pro roles using the [DeleteRoleMemberships](https://docs.aws.amazon.com/quicksight/latest/APIReference/API_DeleteRoleMemberships.html) API. + To update or remove Pro users using the Quick console: 1. Open the [Quick console](https://quicksight.aws.amazon.com/). 1. Choose the profile icon, then choose **Manage Quick**. 1. If necessary, in the left navigation pane, choose **Manage users**. + If you use Quick identity (with or without IAM federation), update user roles or delete users using the steps in [Viewing Amazon Quick account details](managing-user-access-qs-iam.md#view-user-accounts) or [Deleting a Amazon Quick user account](managing-user-access-qs-iam.md#delete-a-user-account). + If you use IAM Identity Center or Microsoft Active Directory, update group and role mappings or delete user groups using the steps in [Managing user access](managing-user-access-idc.md#view-user-accounts-enterprise). 1. Ensure there are no topics in the account by performing the following steps: 1. Use the [ListTopics](https://docs.aws.amazon.com/quicksight/latest/APIReference/API_ListTopics.html) API to list all topics in the account for each AWS Region where topics are used. 1. For each topic, do one of the following: + If you are an owner or co-owner of the topics, delete the topics using the [DeleteTopic](https://docs.aws.amazon.com/quicksight/latest/APIReference/API_DeleteTopic.html) API. + If you're not an owner or co-owner of the topics: + Identify the owners of each topic using the [DescribeTopicPermissions](https://docs.aws.amazon.com/quicksight/latest/APIReference/API_DescribeTopicPermissions.html) API, then ask them to delete their topics using the [DeleteTopic](https://docs.aws.amazon.com/quicksight/latest/APIReference/API_DeleteTopic.html) API. + Make yourself a co-owner of the topics using the [UpdateTopicPermissions](https://docs.aws.amazon.com/quicksight/latest/APIReference/API_UpdateTopicPermissions.html) API , then delete the topics using the [DeleteTopic](https://docs.aws.amazon.com/quicksight/latest/APIReference/API_DeleteTopic.html) API. 1. Ensure that dashboard and visual indexing and Dashboard Q&A are disabled by performing the following steps: + To disable dashboard and visual indexing and Dashboard Q&A using APIs: 1. Disable dashboard and visual indexing using the [UpdateQuickSightQSearchConfiguration](https://docs.aws.amazon.com/quicksight/latest/APIReference/API_UpdateQuickSightQSearchConfiguration.html) API. 1. Disable Dashboard Q&A using the [UpdateDashboardsQAConfiguration](https://docs.aws.amazon.com/quicksight/latest/APIReference/API_UpdateDashboardsQAConfiguration.html) API. + To disable dashboard and visual indexing and Dashboard Q&A using the Quick console: 1. Open the [Quick console](https://quicksight.aws.amazon.com/). 1. Choose the profile icon, then choose **Manage Quick**. 1. Under the **Account** section, choose **Amazon Q**. 1. Disable each of the options. # Working with Amazon Quick Sight Topics Working with Topics | | | --- | |  Applies to: Enterprise Edition  | | | | --- | |    Intended audience: Amazon Quick administrators and authors  | *Topics* are collections of one or more datasets that represent a subject area that your business users can ask questions about. With Quick Sight automated data prep, you get an ML-powered assist to help you create a topic that is relevant to your end users. The first process begins with automated field selection and classification, something like this: + Automated data prep chooses a small number of fields to include by default to create a focused data space for readers to explore. + Automated data prep selects fields that you use in other assets like reports and dashboards. + Automated data prep also imports any additional fields from any related analysis where a topic is enabled. + It identifies dates, dimensions, and measures, to learn how fields can be used in answers. This automatic set of fields help the author quickly get started with natural language analytics. Authors can always exclude fields, or include additional fields, as needed by using the **Include** toggle. Next, automated data prep continues with the process by automatically labeling fields and identifying synonyms. Automated data prep updates field names with friendly names and synonyms using common terms. For example, a `SLS_PERSON` field might be renamed to `Sales person`, and assigned synonyms including: `salesman`, `saleswoman`, agent, and `sales representative`. Although you can let automated data prep do much of the work, it's worthwhile to review the fields, names, and synonyms to further customize them for your end users. For example, if the users refer to a sales person as a "rep" or a "dealer" in casual conversation, then you support this term by adding `rep` and `dealer` to the synonyms for `SLS_PERSON`. Finally, automated data prep detects the semantic type of each field, by sampling its data and examining the formats applied to it by the author during analysis. Automated data prep updates the field configuration automatically, setting formats for values used for each field. Answers to questions are thus provided in expected formats for dates, currencies, identifiers, Booleans, persons, and so on. To learn more about working with topics, continue on to the following sections in this chapter. **Topics** + [ # Navigating Topics ](navigating-topics.md) + [ # Creating Quick Sight topics ](topics-create.md) + [ # Topic workspace ](topics-interface.md) + [ # Working with datasets in an Quick Sight topic ](topics-data.md) + [ # Making Quick Sight topics natural-language-friendly ](topics-natural-language.md) + [ # Sharing Quick Sight topics ](topics-sharing.md) + [ # Managing Amazon Quick Sight topic permissions ](topics-sharing-permissions.md) + [ # Reviewing Quick Sight topic performance and feedback ](topics-performance.md) + [ # Refreshing Quick Sight topic indexes ](topics-index.md) + [ # Work with Quick Sight topics using the Amazon Quick Sight APIs ](topics-cli.md) # Navigating Topics In Quick Sight, there is more than one way to create and manage a topic. You can begin on an Amazon Quick home or "start" page. Or, you can begin inside of an analysis. **Topics** + [ # From an Amazon Quick home page ](starting-from-home.md) + [ # From an Amazon Quick Sight analysis ](starting-from-sheets.md) + [ # Navigating questions in an Amazon Quick Sight analysis ](starting-from-questions-on-sheets.md) # From an Amazon Quick home page From your Quick start page, you can create and manage topics by selecting **Topics** in the navigation pane at left. Quick provides a guided workflow for creating topics. You can step out of the guided workflow and come back to it later, without disrupting your work. When you create a topic, your business users can ask questions about it. At any time, you can open a topic to change it or review how it's performing. To open a topic, choose the topic name. If at any time you want to return to a list of all your topics, choose **All topics** at left of the topic workspace. # From an Amazon Quick Sight analysis To start from an Amazon Quick Sight analysis, open the analysis that you want to use with automated data prep . To open or create a topic, choose the topic icon in the top navigation bar. At any time, you can open a topic to change it or review how it's performing. To open a topic from an analysis, choose the topic name in the top navigation bar, if it isn't already displayed. Then select the vertical ellipsis icon (` ⋮ `) on the top navigation bar. To view information about the topic, select **About topic**. To view the data fields included in the topic, select **Data fields** in the tab list. # Navigating questions in an Amazon Quick Sight analysis Navigating questions and answers By navigating through the questions and answers for a topic in an analysis, you can learn how the topic is being used. This information can inform you to make adjustments if necessary. Starting from within an analysis that is already linked to a topic, select the search bar on the top navigation bar and then enter a question. The answer displays on a topic screen that also displays all the available options to work with the topic in an analysis. + To change the type of visual displayed in the answer, select the type icon (which resembles a bar chart). + To view improvement suggestions, select the speech bubble, which is highlighted if you have unviewed suggestions. + To view insights related to a question, select the light bulb icon. + To add or remove a question from the pinboard, toggle the icon for **Add to pinboard** or **Remove from pinboard**. You can view the pinboard by selecting the pinboard icon from the top navigation bar. + To view information about this topic, select the circled lowercase *i* (` ![\[alt text not found\]](http://docs.aws.amazon.com/quick/latest/userguide/images/status-info.png) `). + Select the ellipsis menu ( ` … `) to do one of the following actions: + **Export to CSV** – Export the data displayed in the selected visual. + **Copy Request ID** – Capture the request ID of this process for troubleshooting. Amazon Quick Sight generates an alphanumeric request ID to uniquely identify each process. + **Share this visual** – Securely share a URL for the topic used in the visual. + **Answer breakdown** – To view a detailed explanation of your answer. At the bottom of the topic screen, you can add or change variations on the question by selecting **Edit question variants**. Also at the bottom, when you are satisfied with the question and answer, mark the topic as reviewed by choosing **Mark as reviewed**. Or, if you see that a previously reviewed topic needs further review, choose **Unmark as reviewed**. At any time, you can open a topic to change it or review how it's performing. To work directly with the settings for a topic, such as which fields are included, or what synonyms they have, use the **Topics** page. **To open a topic linked to an analysis** 1. Open the Amazon Quick Sight **Topics** page from the Quick start page, by selecting **Topics** in the navigation pane at left. If you want to keep your analysis open, you can open the **Topics** page in a new browser tab or window. 1. To open a topic, choose the topic name. If you recently navigated away from the analysis page, the name is probably still displayed in the search bar at the top of the screen. 1. If at any time you want to return to a list of all your topics, choose **All topics** at left of the topic workspace. # Creating Quick Sight topics Creating topics | | | --- | |  Applies to: Enterprise Edition  | | | | --- | |    Intended audience: Amazon Quick administrators and authors  | To turn on questions for your datasets, you have to create a topic. Quick Sight provides a guided workflow for creating topics. You can step out of the guided workflow and come back to it later, without disrupting your work. There are two ways to create a topic: + Create the topic by selecting a dataset. When you create topics in Quick Sight, you can add multiple datasets to them and also enable the topics in analyses. + Create the topic using an analysis. When you create a topic in an analysis, or link an existing topic to an analysis, automated data prep learns from how you analyze your data and automatically applies this to your topic. After you share your topic with Quick readers and they use it to ask questions in the search bar, you can see a summary of how the topic is performing. You can also see a list of everything users asked and how well it was responded to, and any answers you have verified. Reviewing the feedback is important so that your business users can continue to be provided with the correct visualizations and answers to their questions. ## Creating a topic Use the following procedure to create a topic. **To create a topic** 1. On the Quick homepage, choose **Topics**. 1. On the **Topics** page that opens, choose **Create Topic** at upper right. 1. On the **Create Topic** page that opens, do the following: 1. For **Topic name**, enter a descriptive name for the topic. Your business users identify the topic by this name and use it to ask questions. 1. For **Description**, enter a description for the topic. Your users can use this description to get more details about the topic. 1. Choose **Continue**. 1. On the **Add data to topic** page that opens, choose one of the following options: + To add one or more datasets that you own or have permission to, choose **Datasets**, and then select the dataset or datasets that you want to add. + To add datasets from dashboards that you have created or that have been shared with you, choose **Datasets from a dashboard**, and then select a dashboard from the list. 1. Choose **Add data**. Your topic is created and the page for that topic opens. The next step is to configure the topic metadata to make it natural-language-friendly for your readers. For more information, see [Making Quick Sight topics natural-language-friendly](topics-natural-language.md). Or continue to the next topic to explore the topic workspace. # Topic workspace | | | --- | |  Applies to: Enterprise Edition  | | | | --- | |    Intended audience: Amazon Quick administrators and authors  | After you create a topic, or when you choose an existing topic from the list on the **Topics** page, the topic opens to that topic's workspace. Four tabs appear here that you can use as described in the following sections. Quick Sight provides a guided workflow for topics. You can step out of the guided workflow and come back to it later, without disrupting your work. ## Summary The **Summary** tab has three important areas: + **Suggestions** – Suggestions provide step-by-step guidance for how you can improve a topic. These steps help you understand how to create better-performing topics. To follow a suggestion, choose the action button in the Suggestion banner and follow the recommended steps. Currently, there are eight preset suggestions that is offered in the order shown by the following table. After you complete a step for a suggestion, a new suggestion is offered when you return to the **Summary** tab. [\[See the AWS documentation website for more details\]](http://docs.aws.amazon.com/quick/latest/userguide/topics-interface.html) + **Metrics and key performance indicators (KPIs) on topic engagement and performance** – In this section, you can see how your readers engage with your topics and what feedback and ratings they give on the answers provided. You can view engagement for all the questions users asked, or select a specific question. You can also change the time span of the metrics from one year down to one week. For more information, see [Reviewing Quick Sight topic performance and feedback](topics-performance.md). + **Datasets** – This section shows the datasets that were used to create the topic. In this section, you can add additional datasets or import datasets from existing dashboards. You can also edit the metadata for a topic dataset, set a data refresh schedule, change the name of the dataset, and more. For more information, see [Working with datasets in an Quick Sight topic](topics-data.md). ## Data The **Data** tab shows all the fields included in the topic. Here you configure your topic metadata to make your topic natural-language-friendly and to improve your topic performance. For more information, see [Making Quick Sight topics natural-language-friendly](topics-natural-language.md). ## User activity This tab shows all the questions that your topic receives and the overall feedback for each question. You can see an overview of how many questions were asked and what percentage of them were positive and negative. You can filter by feedback and whether someone left a comment with their feedback. For more information, see [Reviewing Quick Sight topic performance and feedback](topics-performance.md). ## Verified answers *Verified answers* are questions that you have preconfigured visuals for. You can create a verified answer to a question by asking the question in the search bar and then marking it as reviewed. By using the **Verified Answers** tab, you can review your verified answers and the feedback they receive by your users. # Working with datasets in an Quick Sight topic Working with datasets in a topic | | | --- | |  Applies to: Enterprise Edition  | | | | --- | |    Intended audience: Amazon Quick administrators and authors  | When you create a topic, you can add additional datasets to it or import datasets from existing dashboards. At any time, you can edit metadata for a dataset and set a data refresh schedule. You can also add new fields to a dataset in a topic by creating calculated fields, filters, or named entities. **Topics** + [ # Adding datasets to a topic in Amazon Quick Sight ](topics-data-add.md) + [ # Adding datasets with row-level security (RLS) to a Amazon Quick Sight topic ](topics-data-rls.md) + [ # Refreshing datasets in a Quick Sight topic ](topics-data-refresh.md) + [ # Removing datasets from a Amazon Quick Sight topic ](topics-data-remove.md) + [ # Adding calculated fields to a Amazon Quick Sight topic dataset ](topics-data-calculated-fields.md) + [ # Adding filters to a Amazon Quick Sight topic dataset ](topics-data-filters.md) + [ # Adding named entities to a Amazon Quick Sight topic dataset ](topics-data-entities.md) # Adding datasets to a topic in Amazon Quick Sight Adding datasets At any time, you can add datasets to a topic. Use the following procedure to learn how. **To add datasets to a topic** 1. Open the topic that you want to add one or more datasets to. 1. On the **Summary** page, choose **Data**. Then, under **Datasets**, choose **Add datasets**. 1. On the **Add datasets** page that opens, choose the dataset or datasets that you want to add, and then choose **Add datasets**. The dataset is added to the topic and the dataset's unique string values are indexed. You can edit the field configurations right away. For more information, see [Refreshing Quick Sight topic indexes](topics-index.md). For more information about editing field configurations , see [Making Quick Sight topics natural-language-friendly](topics-natural-language.md). # Adding datasets with row-level security (RLS) to a Amazon Quick Sight topic You can add datasets that contain row-level security (RLS) to topics. All fields in a topic respect the RLS rules applied to your dataset. For example, if a user asks, "show me sales by region," the data that is returned is based on the user's access to the underlying data. So, if they're only allowed to see the East region, only data for the East region appears in the answer. RLS rules are applied to automatic suggestions when users are asking questions. As users enter questions, only the values that they have access to are suggested to them. If a user enters a question about a dimensional value that they don't have access to, they do not get an answer for that value. For example, suppose that the same user is entering the question, "show me sales in the West region." In this case, they do not get a suggestion or an answer for it, even if they ask, because they don't have RLS access to that region. By default, Quick Sight allows users to ask questions regarding fields based on the user's permissions in RLS. Continue to use this option if your field contains sensitive data that you want to restrict access to. If your fields don't contain sensitive information and you want all users to see the information in suggestions, then you can choose to allow questions for all values in the field. **To allow questions for all fields** 1. From the Quick homepage, choose **Data**. 1. Under the **Datasets** tab, choose the dataset that you added RLS to, and then choose **Edit dataset**. For more information about adding RLS to a dataset, see [Using row-level security in Amazon Quick](row-level-security.md). 1. On the data preparation page, choose the field menu (the three dots) for a field that you want to allow , and then choose **Row level security **. 1. On the **Row level security for Quick** page that opens, choose **Allow users to ask questions regarding all values on this field**. 1. Choose **Apply**. 1. When finished editing the dataset, choose **Save & publish** in the blue toolbar at upper right. 1. Add the dataset to your topic. For more information, see the previous section, [Adding datasets to a topic in Amazon Quick Sight](topics-data-add.md). If you currently allow users to ask questions regarding all values, but want to implement the dataset's RLS rules to protect sensitive information, then repeat steps 1–4 and choose **Allow users to ask questions regarding this field based on their permissions**. When you are done, refresh the dataset in your topic. For more information, see [Refreshing datasets in a Quick Sight topic](topics-data-refresh.md). # Refreshing datasets in a Quick Sight topic Refreshing datasets When you add a dataset to a topic, you can specify how often you want that dataset to refresh. When you refresh datasets in a topic, the index is refreshed for that topic with any new and updated information. Your datasets aren't replicated when you add them to a topic. An index of unique string values is created and metrics are not indexed. For example, measures stored as integers are not indexed. Questions asked always fetch the latest sales metrics based on data in your dataset. For more information about refreshing the topic index, see [Refreshing Quick Sight topic indexes](topics-index.md) You can set a refresh schedule for a dataset in a topic, or refresh the dataset manually. You can also see when the data was last refreshed. **To set a refresh schedule for a topic dataset** 1. Open the topic that you want to change. 1. On the **Summary** page, choose **Data**. Then, under **Datasets**, expand the dataset that you want to set a refresh schedule for. 1. Choose **Add schedule**, and then do one of the following in the **Add refresh schedule** page that opens. + If the dataset is a SPICE dataset, select **Refresh topic when dataset is imported into SPICE**. Currently, hourly refresh SPICE datasets aren't supported. SPICE datasets that are set to refresh every hour are automatically converted to a daily refresh. For more information about setting refresh schedules for SPICE datasets, see [Refreshing SPICE data](refreshing-imported-data.md). + If the dataset is a direct query dataset, do the following: 1. For **Timezone**, choose a time zone. 1. For **Repeats**, choose how often you want the refresh to happen. You can choose to refresh the dataset daily, weekly, or monthly. 1. For **Refresh time**, enter the time that you want the refresh to start. 1. For **Start first refresh on**, choose a date that you want start refreshing the dataset on. 1. Choose **Save**. **To manually refresh a dataset** 1. On the topic **Summary** page, choose **Data**. Then, under **Datasets**, choose the dataset that you want to refresh. 1. Choose **Refresh now**. **To view refresh history for a dataset** 1. On the topic **Summary** page, choose **Data**. Then, under **Datasets**, choose the dataset that you want to see refresh history for. 1. Choose **View history**. The **Update history** page opens with a list of the times the dataset was refreshed. # Removing datasets from a Amazon Quick Sight topic Removing datasets You can remove datasets from a topic. Removing datasets from a topic doesn't delete them from Quick Sight. Use the following procedure to remove a dataset from a topic. **To remove a dataset from a topic** 1. Open the topic that you want to change. 1. On the **Summary** page, choose **Data**. Then, under **Datasets**, choose the dataset menu (the three dots) at right, and then choose **Remove from topic**. 1. On the **Are you sure you want to delete?** page that opens, choose **Delete** to remove the dataset from the topic. Choose **Cancel** if you don't want to remove the dataset from the topic. # Adding calculated fields to a Amazon Quick Sight topic dataset Adding calculated fields You can create new fields in a topic by creating calculated fields. *Calculated fields* are fields that use a combination of one or two fields from a dataset with a supported function to create new data. For example, if your dataset contains columns for sales and expenses, you can combine them in a calculated field with a simple function to create a profit column. The function might look like the following: `sum({Sales}) - sum({Expenses})`. **To add a calculated field to a topic** 1. Open the topic that you want to change. 1. In the topic, choose the **Data** tab. 1. For **Actions**, choose **Add calculated field**. 1. In the calculations editor that opens, do the following: 1. Give the calculated field a friendly name. 1. For **Datasets** at right, choose a dataset that you want to use for the calculated field. 1. Enter a calculation in the calculation editor at left. You can see a list of fields in the dataset in the **Fields** pane at right. You can also see a list of supported functions in the **Functions** pane at right. For more information about the functions and operators you can use to create calculations in Quick Sight, see the [Calculated field function and operator reference for Amazon QuickFunctions and operators](calculated-field-reference.md). 1. When finished, choose **Save**. The calculated field is added to the list of fields in the topic. You can add a description to it and configure metadata for it to make it more natural language friendly. # Adding filters to a Amazon Quick Sight topic dataset Adding filters Sometimes your business users (readers) might ask questions that contain terms that map to multiple cells of values in the data. For example, let's say one of your readers asks, "Show me weekly sales trend in the west." *West* in this instance refers to both the `Northwest` and `Southwest` values in the `Region` field, and requires the data to be filtered to generate an answer. You can add filters to a topic to support requests like these. **To add a filter to a topic** 1. Open the topic that you want to add a filter to. 1. In the topic, choose the **Data** tab. 1. For **Actions**, choose **Add filter**. 1. In the **Filter configuration** page that opens, do the following: 1. For **Name**, enter a friendly name for the filter. 1. For **Dataset**, choose a dataset that you want to apply the filter to. 1. For **Field**, choose the field that you want to filter. Depending on the type of field you choose, you're offered different filtering options. + If you chose a text field (for example, `Region`), do the following: 1. For **Filter type**, choose the type of filter that you want. For more information about filter text fields, see [Adding text filters](add-a-text-filter-data-prep.md). 1. For **Rule**, choose a rule. 1. For **Value**, enter one or more values. + If you chose a date field (for example, `Date`), do the following: 1. For **Filter type**, choose the type of filter that you want, and then enter the date or dates that you want to apply the filter to. For more information about filtering dates, see [Adding date filters](add-a-date-filter2.md). + If you chose a numeric field (for example, `Compensation`), do the following: 1. For **Aggregation**, choose how you want to aggregate the filtered values. 1. For **Rule**, choose a rule for the filter, and then enter a value for that rule. For more information about filtering numeric fields, see [Adding numeric filters](add-a-numeric-filter-data-prep.md). 1. (Optional) To specify when the filter is applied, choose **Apply the filter anytime the dataset is used**, and then choose one of the following: + **Apply always** – When you choose this option, the filter is applied whenever any column from the dataset you specified is linked to a question. + **Apply always, unless a question results in an explicit filter from the dataset** – When you choose this option, the filter is applied whenever any column from the dataset you specified is linked to a question. However, if the question mentions an explicit filter on the same field, the filter isn't applied. 1. When finished, choose **Save**. The filter is added to the list of fields in the topic. You can edit the description for it or adjust when the filter is applied. # Adding named entities to a Amazon Quick Sight topic dataset Adding named entities When asking questions about your topic, your readers might refer to multiple columns of data without stating each column explicitly. For example, they might ask for the address of a transaction. What they actually mean is that they want the branch name, state, and city of where the transaction was made. To support requests like this, you can create a named entity. A *named entity* is a collection of fields that display together in an answer. For example, using the transaction address example, you can create a named entity called `Address`. You can then add the `Branch Name`, `State`, and `City` columns to it, which already exist in the dataset. When someone asks a question about address, the answer displays the branch, state, and city where a transaction took place. **To add a named entity to a topic** 1. Open the topic that you want to change. 1. In the topic, choose the **Data** tab. 1. For **Actions**, choose **Add named entity**. 1. In the **Named entity** page that opens, do the following: 1. For **Dataset**, choose a dataset. 1. For **Name**, enter a friendly name for the named entity. 1. For **Description**, enter a description of the named entity. 1. (Optional) For **Synonyms**, add any alternate names that you think your readers might use to refer to the named entity or the data it contains. 1. Choose **Add field**, and then choose a field from the list. Choose **Add field** again to add another field. The ordering of the fields listed here are the order they appear in answers. To move a field, choose the six dots at left of the field name and drag and drop the field to the order that you want. 1. When finished, choose **Save**. The named entity is added to the list of fields in the topic. You can add edit the description for it and add synonyms to it to make it more natural language friendly. # Making Quick Sight topics natural-language-friendly Making topics natural-language-friendly | | | --- | |  Applies to: Enterprise Edition  | | | | --- | |    Intended audience: Amazon Quick administrators and authors  | When you create a topic, Quick Sight creates, stores, and maintains an index with definitions for data in that topic. This index is used to generate correct answers, provide autocomplete suggestions when someone asks a question, and suggest mappings of terms to columns or data values. This is how key terms can be interpreted in your readers' questions and mapped to your data. To help interpret your data and better answer your readers' questions, provide as much information about your datasets and their associated fields as possible. Use the following procedures to do so, making your topics more natural-language-friendly. **Tip** You can edit multiple fields at a time using bulk actions. Use the following procedure to bulk-edit fields in a topic. **To bulk-edit fields in a topic** 1. Open the topic that you want to change. 1. In the topic, choose the **Data** tab. 1. Under **Fields**, select two or more fields that you want to change. 1. Choose **Bulk Actions** at the top of the list. 1. In the **Bulk Actions** page that opens, configure the fields how you want, and then choose **Apply to**. The configuration options are described in the following steps. ## Step 1: Give datasets friendly names and descriptions Dataset names are often based on technical naming conventions that your readers might not naturally use to refer to them. We recommend that you give your datasets friendly names and descriptions to provide more information about the data they contain. These friendly names and descriptions are used to understand dataset contents and select a dataset based on the reader's question. The dataset names are also shown to the reader to provide additional context for an answer. For example, if your dataset is named `D_CUST_DLY_ORD_DTL`, you might rename it in the topic to `Customer Daily Order Details`. That way, when your readers see it listed in the search bar for your topic, they can quickly determine if the data is relevant to them or not. **To give a dataset a friendly name and description** 1. Open the topic that you want to change. 1. On the **Summary** tab, choose **Data**. Then, under **Datasets**, choose the down arrow at the far right of the dataset to expand it. 1. Choose the pencil icon next to the dataset name at left, and then enter a friendly name. We recommend using a name that your readers will understand. 1. For **Description**, enter a description for the dataset that describes the data it contains. ## Step 2: Instruct how to use date fields in your datasets If your dataset contains date and time information, we recommend instructing how to use that information when answering questions. Doing this is especially important if you have multiple date time columns in a topic. In some cases, there are multiple valid date columns in a topic, such as order date and shipped date. In these cases, you can help readers by specifying a default date to use to answer their questions. Readers can choose a different date if the default date doesn't answer their question. You can also tell how granular to be with your date time columns by specifying a time basis. The *time basis* for a dataset is the lowest level of time granularity that is supported by all measures in the dataset. This setting helps aggregate metrics in the dataset across different time dimensions and is applicable for datasets that support a single date time granularity. This option can be set for denormalized datasets with a large number of metrics. For example, if a dataset supports several metrics at a daily aggregation, then you can set the time basis of that dataset to **Daily**. This is then used to determine how to aggregate metrics. **To set a default date and time basis for a dataset** 1. Open the topic that you want to change. 1. On the **Summary** tab, choose **Data**. Then, under **Datasets**, choose the down arrow at far right of the dataset to expand it. 1. For **Default date**, choose a date field. 1. For **Time basis** choose the lowest level of granularity that you want to aggregate metrics in the dataset to. You can aggregate metrics in a topic at the daily, weekly, monthly, quarterly, or yearly level. ## Step 3: Exclude unused fields When you add a dataset to a topic, all columns (fields) in the dataset are added by default. If your dataset contains fields that you or your readers don't use, or that you don't want to include in answers, you can exclude them from the topic. Excluding these fields removes them from answers and the index and improves the accuracy of answers that your readers receive. **To exclude fields in a topic** 1. Open the topic that you want to change. 1. In the topic, choose the **Data** tab. 1. In the **Fields** section, under **Include**, toggle the icon off. ## Step 4: Rename fields to be natural-language-friendly Fields in a dataset are often named based on technical naming conventions. You can make your field names more user-friendly in your topics by renaming them and adding descriptions. Field names are used to understand the fields and link them to terms in your readers' questions. When your field names are user-friendly, it's easier to draw links between the data and a reader’s question. These friendly names are also presented to readers as part of the answer to their question to provide additional context. **To rename and add descriptions to a field** 1. Open the topic that you want to change. 1. In the topic, choose the **Data** tab. 1. In the **Fields** section, choose the down arrow at far right of the field to expand it. 1. Choose the pencil icon next to the field name at left, and then enter a friendly name. 1. For **Description**, enter a description of the field. ## Step 5: Add synonyms to fields and field values Even if you update your field names to be user-friendly and provide a description for them, your readers might still use different names to refer to them. For example, a `Sales` field might be referred to as `revenue`, `rev`, or `spending` in your reader's questions. To help make sense of these terms and map them to the correct fields, you can add one or more synonyms to your fields. Doing this improves accuracy. As with field names, your readers might use different names to refer to specific values in your fields. For example, if you have a field that contains the values `NW`, `SE`, `NE`, and `SW`, you can add synonyms for those values. You can add `Northwest` for `NW`, `Southeast` for `SE`, and so on. **To add synonyms for a field** 1. Open the topic that you want to change. 1. In the topic, choose the **Data** tab. 1. In the **Fields** section, under **Synonyms**, choose the pencil icon for the field, enter a word or phrase, and then press Enter on your keyboard. To add another synonym, choose the **\$1** icon. **To add synonyms for a value in a field** 1. Open the topic that you want to change. 1. In the topic, choose the **Data** tab. 1. In the **Fields** section, choose the down arrow at far right to expand information about the field. 1. Under **Value Preview** at right, choose **Configure value synonyms**. 1. On the **Field Value Synonyms** page that opens, choose **Add**, and then do the following: 1. For **Value**, choose the value that you want to add synonyms to. 1. For **Synonyms**, enter one or more synonyms for the value. 1. Choose **Save**. 1. To add synonyms for another value, repeat steps 5–6. 1. When you finish, choose **Done**. ## Step 6: Explain more about your fields To help interpret how to use your data to answer readers' questions, you can explain more about the fields in your datasets. You can say whether a field in your dataset is a dimension or a measure and specify how that field should be aggregated. You can also clarify how the values in a field should be formatted, and what type of data is in the field. Configuring these additional settings helps create accurate answers for your readers when they ask a question. Use the following procedures to explain more about your fields. ### Assign field roles Every field in your dataset is either a dimension or a measure. *Dimensions* are categorical data, and *measures* are quantitative data. Knowing whether a field is a dimension or a measure determines what operations can and can't perform on a field. For example, setting the fields `Patient ID`, `Employee ID`, and `Ratings` helps interpret those fields as integers. This setting means that the fields will not be aggregated as they are measured. **To set a field role** 1. Open the topic that you want to change. 1. In the topic, choose the **Data** tab. 1. In the **Fields** section, choose the down arrow at far right to expand information about the field. 1. For **Role**, choose a role. You can choose a measure or a dimension. 1. (Optional) If your measure is inversely proportional (for example, the lower the number, the better), choose **Inverted measure**. This explains how to interpret and display the values in this field. ### Set field aggregations Setting field aggregations helps determine which function should or shouldn't be used when those fields are aggregated across multiple rows. You can set a default aggregation for a field, and a not allowed aggregation. A *default aggregation* is the aggregation that's applied when there's no explicit aggregation function mentioned or identified in a reader's question. For example, let's say one of your readers asks, "How many products were sold yesterday?" In this case, Q uses the field `Product ID`, which has a default aggregation of `count distinct`, to answer the question. Doing this results in a visual showing the distinct count of Product ID. *Not allowed aggregations* are aggregations that are excluded from being used on a field to answer a question. They're excluded even if the question specifically asks for a not allowed aggregation. For example, let's say you specify that the `Product ID` field should never be aggregated by `sum`. Even if one of your readers asks, "How many total products were sold yesterday?" `sum` isn't used to answer the question. If aggregate functions are incorrectly applied on a field, we recommend that you set not allowed aggregations for the field. **To set field aggregations** 1. Open the topic that you want to change. 1. In the topic, choose the **Data** tab. 1. In the **Fields** section, choose the down arrow at far right to expand information about the field. 1. For **Default aggregation**, choose the aggregation that you want to aggregate the field by default. You can aggregate measures by sum, average, max, and min. You can aggregate dimensions by count and count distinct. 1. (Optional) For **Not allowed aggregations**, choose an aggregation that you don't want to use. 1. (Optional) If you don't want to aggregate the field in a filter, choose **Never aggregate in a filter**. ### Specify how to format field values If you want to explain how to format the values in your fields, you can do so. For example, suppose that you have the field `Order Sales Amount`, which contains values that you want to format as U.S. dollars. In this case, you can explain how to format the values in the field as U.S. currency when used in answers. **To specify how to format field values** 1. Open the topic that you want to change. 1. In the topic, choose the **Data** tab. 1. In the **Fields** section, choose the down arrow at far right to expand information about the field. 1. For **Value format**, choose how you want to format the values in the field. ### Specify field semantic types A field *semantic type* is the type of information represented by the data in a field. For example, you might have a field that contains location data, currency data, age data, or Boolean data. You can specify a semantic type and additional semantic subtype for fields. Specifying these helps to understand the meaning of the data stored in your fields. Use the following procedure to specify field semantic types and subtypes. **To specify field semantic types** 1. Open the topic that you want to change. 1. In the topic, choose the **Data** tab. 1. In the **Fields** section, choose the down arrow at far right to expand information about the field. 1. For **Semantic type**, choose the kind of information the data represents. For measures, you can select duration, date part, location, boolean, currency, percentage, age, distance, and identifier types. For dimensions, you can select date part, location, Boolean, person, organization, and identifier types. 1. For **Semantic sub-type**, choose an option to further specify the kind of information the data represents. The options here depend on the semantic type that you chose and the role associated with the field. For a list of semantic types and their associated subtypes for measures and dimensions, see the following table. | Semantic Type | Semantic Subtype | Available for the Following | | --- | --- | --- | | Age | | Measures | | Boolean | | Dimensions and measures | | Currency | USD EUR GBP | Measures | | Date part | Day Week Month Year Quarter | Dimensions and measures | | Distance | Kilometer Meter Yard Foot | Measures | | Duration | Second Minute Hour Day | Measures | | Identifier | | Dimensions and measures | | Location | Zip code Country State City | Dimensions and measures | | Organization | | Dimensions | | Percentage | | Measures | | Person | | Dimensions | # Sharing Quick Sight topics Sharing topics | | | --- | |  Applies to: Enterprise Edition  | | | | --- | |    Intended audience: Amazon Quick administrators and authors  | After you create a topic, you can share it with others in your organization. Sharing a topic allows your users to select the topic and ask questions about it in the search bar. After you share a topic with your users, you can assign permissions to them that specify who can change the topic. **To share a topic** 1. On the Quick start page, choose **Topics** at left. 1. On the **Topics** page that opens, open the topic that you want to share. 1. On the page that opens, choose **Share** at upper right. 1. On the **Share topic with users** page that opens, choose the user or users that you want to share the topic with. You can use the search bar to search for users by email address. 1. Choose either **Viewer** or **Co-owner** under the **Permission** column to assign permissions to your users. For more information about these permissions, see the following section, [Managing Amazon Quick Sight topic permissions](topics-sharing-permissions.md). 1. When you're finished selecting users, choose **Share**. # Managing Amazon Quick Sight topic permissions Manage topic permissions When you share your topics with others in your organization, you might want to control who can change them. To do this, specify which users are viewers and which are co-owners. *Viewers* can see the topic in the search bar when they select a topic from the list, but they can't change the topic data. *Co-owners* can see the topic in the search bar, and they can also change the topic. **To assign topic permissions to your users** 1. From the Quick start page, choose **Topics**. 1. On the **Topics** page that opens, open the topic that you want to manage permissions for. 1. On the topic page that opens, choose **Share** at upper right. 1. On the **Share topic with users** page that opens, choose **Manage topic access**. 1. On the **Manage topic permissions** page that opens, find the user that you want to manage access for, and then for **Permission**, choose one of the following options: + To allow a user to view and change the topic, choose **Co-Owner**. + To allow a user to view the topic only, choose **Viewer**. # Reviewing Quick Sight topic performance and feedback Reviewing topic performance and feedback | | | --- | |  Applies to: Enterprise Edition  | | | | --- | |    Intended audience: Amazon Quick administrators and authors  | After you create a topic and share it with your users, you can review how that topic is performing. When someone uses your topic to ask a question or provides feedback on how well the response was, it's recorded on the topic's **Summary** and **User Activity** tabs. On the topic's **Summary** tab, you can view historical data for the number of questions asked over time, in time periods from seven days to a year. You can also see a distribution of questions that received positive, negative, or no feedback, and also questions that were unanswerable. On the **User Activity** tab, you can see a list of the questions that users asked and any positive or negative feedback and comments that they left. Reviewing this information can help you determine whether your topic is meeting your users' needs. For example, let's say you have a topic that's receiving a lot of negative feedback from your users. When you review your user activity, you notice that several users are leaving comments on a question that showed them the wrong data. In response, you examine the questions that they asked, and notice that they were using a term that you didn't anticipate. You decide to add that term as a synonym to the correct field in the topic. Over time, you notice an increase in positive feedback. ## Reviewing topic performance Use the following procedure to view how a topic is performing. **To view how a topic is performing** 1. On the Quick start page, choose **Topics** at left. 1. On the **Topics** page that opens, open the topic that you want to review. The topic opens and the **Statistics** section shows the topic's statistics. 1. (Optional) To change the amount of historical data shown in the chart, choose one of the following options: **7 days**, **30 days**, **90 days**, **120 days**, or **12 months**. 1. (Optional) To remove questions that were unanswerable from the data, clear **Include Unanswerable data**. 1. (Optional) To remove questions that didn't receive feedback from the data, clear **Include No feedback data**. ## Reviewing topic questions and feedback Use the following procedures to review a topic's questions and feedback. **To review topic questions and feedback** 1. On the Quick start page, choose **Topics**. 1. On the **Topics** page that opens, open the topic that you want to review feedback for. 1. On the topic's page that opens, choose the **User Activity** tab. The user activity for the topic is shown. At the top, you can see the total number of questions asked and the number of questions that were answerable and unanswerable. You can also see the percentage of questions that were rated positive and negative. Additionally, you can see the percentage of questions that were disambiguated. This means that someone entered a question and mapped one of the words in the question to a field in the topic. You can choose any of these statistics to filter the list of questions. 1. (Optional) To view a comment left by a user on a question, choose the down arrow at right of the question. The comment is shown at left. 1. (Optional) To view the fields used to respond to a question, choose the down arrow at right of the question. The fields used are shown at right. Choose a field name to edit its metadata. 1. (Optional) To view a question that was disambiguated, choose the down arrow at right of a question with a term highlighted in red. A description of the term and the field that was used to disambiguate it is shown. To add synonyms for the field, choose **Add synonyms**. 1. (Optional) To view how a question was responded to, choose **View** next to the question in the list. 1. (Optional) To filter the list of questions, choose **Filter by** at right, and then filter by one of the following options. + **See all questions** – This option removes all filters and shows all questions that a topic has received. + **Answerable** – This option filters the list of questions to those that were answerable. Answerable questions are questions that Q was able to respond to. + **Unanswerable** – This option filters the list of questions to those that were unanswerable. Unanswerable questions are questions that Q could not respond to. + **Disambiguated** – This option filters the list of questions to those that were disambiguated, meaning questions with terms that users manually mapped a field to. + **No feedback** – This option filters the list of questions to those that didn't receive feedback. + **Negative** – This option filters the list of questions to those that received negative feedback. + **Positive** – This option filters the list of questions to those that received positive feedback. + **No comments** – This option filters the list of questions to those that didn't receive comments from users. + **Has comments** – This option filters the list of questions to those that received comments from users. + **User** – This option filters the list of questions to those that were asked by a user with a specific user name that you enter. # Refreshing Quick Sight topic indexes Refreshing topic indexes | | | --- | |  Applies to: Enterprise Edition  | | | | --- | |    Intended audience: Amazon Quick administrators and authors  | When you create a topic, Quick Sight creates, stores, and maintains an index with definitions for data in that topic. This index isn't exposed to Quick Sight authors. It's not a copy of the datasets included in a topic either. Metrics are not indexed. For example, measures stored as integers are not indexed. The topic index is an index of unique string values for fields included in a topic. This index is used to generate correct answers, provide autocomplete suggestions when someone asks a question, and suggest mappings of terms to columns or data values. To refresh a topic index, refresh the datasets in the topic. You can manually refresh all datasets in a topic or refresh an individual dataset. You can also view dataset refresh history to monitor past refreshes, and set a recurring refresh schedule for every dataset in the topic. For SPICE datasets, you can sync the topic index refresh schedule with the SPICE refresh schedule. For more information about setting SPICE refresh schedules, see [Refreshing a dataset on a schedule](refreshing-imported-data.md#schedule-data-refresh). **Note** Currently, hourly refresh schedules aren't supported. You can set a refresh schedule to refresh datasets in a topic up to once a day. We recommend that you update topic indexes regularly to ensure that the latest definitions and values are recorded. Updating a topic index takes approximately 15 to 30 minutes, depending on the number and size of datasets included in the topic. **To refresh a topic index** 1. On the Quick start page, choose **Topics**. 1. On the **Topics** page that opens, open the topic that you want to refresh. The topic opens to the **Summary** tab, which shows the datasets that are included in the topic at page bottom. It also shows when the last time the topic was refreshed at upper right. 1. Choose **Refreshed** at upper right to refresh the topic index, and then choose **Refresh data**. Doing this manually refreshes all datasets in the topic. For more information about refreshing individual datasets in a topic, see [Refreshing datasets in a Quick Sight topic](topics-data-refresh.md). # Work with Quick Sight topics using the Amazon Quick Sight APIs Using the Amazon Quick Sight APIs | | | --- | |  Applies to: Enterprise Edition  | | | | --- | |    Intended audience: Amazon Quick developers  | Use this section to learn how to work with Quick Sight topics using the Amazon Quick Sight command line interface (CLI). **Prerequisites** Before you begin, make sure that you have an AWS Identity and Access Management (IAM) role that grants the CLI user access to call the Quick Sight API operations. The following table shows which permissions must be added to the IAM policy to use specific API operations. To use all of the topic API operations, add all of the permissions listed in the table. | API operation | IAM policy | | --- | --- | | `CreateTopic` | `quicksight:CreateTopic` `quicksight:PassDataSet` | | `ListTopics` | `quicksight:ListTopics` | | `DescribeTopic` | `quicksight:DescribeTopic` | | `DescribeTopicPermissions` | `quicksight:DescribeTopicPermissions` | | `DescribeTopicRefresh` | `quicksight:DescribeTopicRefresh` | | `DeleteTopic` | `quicksight:DeleteTopic` | | `UpdateTopic` | `quicksight:UpdateTopic` `quicksight:PassDataSet` | | `UpdateTopicPermissions` | `quicksight:UpdateTopicPermissions` | | `CreateTopicRefreshSchedule` | `quicksight:CreateTopicRefreshSchedule` | | `ListTopicRefreshSchedules` | `quicksight:ListTopicRefreshSchedules` | | `DescribeTopicRefreshSchedule` | `quicksight:DescribeTopicRefreshSchedule` | | `UpdateTopicRefreshSchedule` | `quicksight:UpdateTopicRefreshSchedule` | | `DeleteTopicRefreshSchedule` | `quicksight:DeleteTopicRefreshSchedule` | | `BatchCreateTopicReviewedAnswer` | `quicksight:BatchCreateTopicReviewedAnswer` | | `BatchDeleteTopicReviewedAnswer` | `quicksight:BatchDeleteTopicReviewedAnswer` | | `ListTopicReviewedAnswers` | `quicksight:ListTopicReviewedAnswers` | The following example shows an IAM policy that allows a user to use the `ListTopics` API operation. ------ #### [ JSON ] **** ``` { "Version":"2012-10-17", "Statement": [ { "Effect": "Allow", "Action": [ "quicksight:ListTopics" ], "Resource": "*" } ] } ``` ------ After you configure the permissions to create Quick Sight topics with the Quick Sight APIs, use the following topics to create and work with Quick Sight topic APIs. **Topics** + [ # Work with Quick Sight topics using the Quick Sight APIs ](topic-cli-examples.md) + [ # Configure Quick Sight topic refresh schedules with the Quick Sight CLI ](topic-refresh-apis.md) + [ # Copy and migrate Quick Sight topics within and between AWS accounts ](topic-cli-walkthroughs.md) + [ # Create and modify reviewed answers in Quick Sight topics with the Quick Sight APIs ](topic-reviewed-answer-apis.md) # Work with Quick Sight topics using the Quick Sight APIs The following example creates a new topic. ``` aws quicksight create-topic --aws-account-id AWSACCOUNTID --topic-id TOPICID --topic TOPIC ``` You can also create a new topic by using a CLI skeleton file with the following command. For more information about CLI skeleton files, see [Using CLI skeleton files](https://docs.aws.amazon.com/quicksight/latest/developerguide/cli-skeletons.html) in the *Amazon Quick Sight Developer Guide*. ``` aws quicksight create-topic --cli-input-json file://createtopic.json ``` When you create a new topic, the dataset refresh configuration is not copied to the topic. To set a topic refresh schedule for your new topic, you can make a `create-topic-refresh-schedule` API call. For more information about configuring topic refresh schedules with the CLI, see [Configure Quick Sight topic refresh schedules with the Quick Sight CLI](topic-refresh-apis.md). After you create your first topic, you can update, delete, list, or request a summary of a topic. The following example updates a topic. ``` aws quicksight update-topic --aws-account-id AWSACCOUNTID --topic-id TOPICID --topic TOPIC ``` You can also update a topic by using a CLI skeleton file with the following command. For more information about CLI skeleton files, see [Using CLI skeleton files](https://docs.aws.amazon.com/quicksight/latest/developerguide/cli-skeletons.html) in the *Amazon Quick Sight Developer Guide*. ``` aws quicksight update-topic --cli-input-json file://updatetopic.json ``` The following example provides a list of all topics in a Quick account. ``` aws quicksight list-topics --aws-account-id AWSACCOUNTID ``` The following example deletes a topic. ``` aws quicksight delete-topic --aws-account-id AWSACCOUNTID --topic-id TOPICID ``` The following example provides information about how a topic was configured. ``` aws quicksight describe-topic --aws-account-id AWSACCOUNTID --topic-id TOPICID ``` The following command updates the permissions of a topic. ``` aws quicksight update-topic-permissions --aws-account-id AWSACCOUNTID --topic-id TOPICID --grant-permissions Principal=arn:aws:quicksight:us-east-1:AWSACCOUNTID:user/default/USERNAME,Actions=quicksight:DescribeTopic --revoke-permissions Principal=arn:aws:quicksight:us-east-1:AWSACCOUNTID:user/default/USERNAME,Actions=quicksight:DescribeTopic ``` Use the `grant-permissions` parameter to grant read and author permissions to Quick account users. To grant read permissions to an account user, enter the following value: `"quicksight:DescribeTopic"`. To grant permissions to an account user, enter the following values: + `"quicksight:DescribeTopic"` + `"quicksight:DescribeTopicRefresh"` + `"quicksight:ListTopicRefreshSchedules"` + `"quicksight:DescribeTopicRefreshSchedule"` + `"quicksight:DeleteTopic"` + `"quicksight:UpdateTopic"` + `"quicksight:CreateTopicRefreshSchedule"` + `"quicksight:DeleteTopicRefreshSchedule"` + `"quicksight:UpdateTopicRefreshSchedule"` + `"quicksight:DescribeTopicPermissions"` + `"quicksight:UpdateTopicPermissions"` The `RevokePermissions` parameter revokes all permissions granted to an account user. The following command describes all permissions from a topic. ``` aws quicksight describe-topic-permissions --aws-account-id AWSACCOUNTID --topic-id TOPICID ``` After you create a Quick Sight topic, you can use the Amazon Quick Sight APIs to [configure a topic refresh schedule](https://docs.aws.amazon.com/quicksuite/latest/userguide/topic-refresh-apis), [migrate Quick Sight topics within or between accounts](https://docs.aws.amazon.com/quicksuite/latest/userguide/topic-cli-walkthroughs), and [ create reviewed answers](https://docs.aws.amazon.com/quicksuite/latest/userguide/topic-reviewed-answer-apis). # Configure Quick Sight topic refresh schedules with the Quick Sight CLI Configure topic refresh schedules The following command creates a refresh schedule of a topic. ``` aws quicksight create-topic-refresh-schedule --aws-account-id AWSACCOUNTID --topic-id TOPICID --dataset-arn DATASETARN --refresh-schedule REFRESHSCHEDULE ``` After you create a refresh schedule for a topic, you can update, delete, list, or request a summary of the topic's refresh schedule. The following command updates the refresh schedule of a topic. ``` aws quicksight update-topic-refresh-schedule --aws-account-id AWSACCOUNTID --topic-id TOPICID --dataset-id DATASETID --refresh-schedule REFRESHSCHEDULE ``` The following example provides a list of all refresh schedules configured to a topic. ``` aws quicksight list-topic-refresh-schedules --aws-account-id AWSACCOUNTID --topic-id TOPICID ``` The following example deletes a topic refresh schedule. ``` aws quicksight delete-topic-refresh-schedule --aws-account-id AWSACCOUNTID --topic-id TOPICID --dataset-id DATASETID ``` The following example provides information about how a topic refresh schedule was configured. ``` aws quicksight describe-topic-refresh-schedule --aws-account-id AWSACCOUNTID --topic-id TOPICID --dataset-id DATASETID ``` # Copy and migrate Quick Sight topics within and between AWS accounts Migrate Quick Sight topics You can migrate your Quick Sight topics from one account to another with the Quick Sight command line interface (CLI). Instead of manually replicating the same topic across multiple dashboards, namespaces, or accounts, you can use the Quick Sight CLI to reuse the same topic repeatedly. This capability saves Quick Sight authors time and creates a standardized topic experience for dashboard readers across multiple dashboards. To migrate topics with the Quick Sight CLI, use the following procedure **To migrate a topic to another account** 1. First, identify the topic that you want to migrate. You can view a list of every topic in your Quick account with a `list-topics` API command. ``` aws quicksight list-topics --aws-account-id AWSACCOUNTID ``` 1. After you have a list of topics, locate the topic that you want to migrate and make a `describe-topic` call to receive a JSON structure of the topic's configuration. ``` aws quicksight describe-topic --aws-account-id AWSACCOUNTID --topic-id TOPICID ``` Following is an example of a `describe-topic` API response. ``` { "Status": 200, "TopicId": "TopicExample", "Arn": "string", "Topic": [ { "Name": "{}", "DataSets": [ { "DataSetArn": "{}", "DataSetName": "{}", "DataSetDescription": "{}", "DataAggregation": "{}", "Filters": [], "Columns": [], "CalculatedFields": [], "NamedEntities": [] } ] } ], "RequestId": "requestId" } ``` 1. Use the JSON response to create a skeleton file that you can input into a new `create-topic` call in your other Quick account. Before you make an API call with your skeleton file, make sure to change the AWS account ID and dataset ID in the skeleton file to match the AWS account ID and dataset ID that you are adding the new topic to. For more information about CLI skeleton files, see [Using CLI skeleton files](https://docs.aws.amazon.com/quicksight/latest/developerguide/cli-skeletons.html) in the *Amazon Quick Sight Developer Guide*. ``` aws quicksight create-topic --aws-account-id AWSACCOUNTID \ --cli-input-json file://./create-topic-cli-input.json ``` After you make a `create-topic` call to the Quick Sight API, the new topic appears in your account. To confirm that the new topic exists, make a `list-topics` call to the Quick Sight API. If the source topic that was duplicated contains verified answers, the answers are not migrated to the new topic. To see a list of all verified answers that are configured to the original topic, use a `describe-topic` API call. # Create and modify reviewed answers in Quick Sight topics with the Quick Sight APIs Create and modify reviewed answers with the Quick Sight APIs After you create a Quick Sight topic, you can use the Quick Sight APIs to create, list, update, and delete reiewed answers for topics. The command below batch creates up to 100 reviewed answers for a Quick Sight topic. ``` aws quicksight batch-create-topic-reviewed-answer \ --topic-id TOPICID \ --aws-account-id AWSACCOUNTID \ —answers ANSWERS ``` You can also batch create reviewed answers from a CLI skeleton file with the following command. For more information about CLI skeleton files, see [Using CLI skeleton files](https://docs.aws.amazon.com/quicksight/latest/developerguide/cli-skeletons.html) in the *Amazon Quick Sight Developer Guide*. ``` aws quicksight batch-create-topic-reviewed-answer \ --cli-input-json file://createTopicReviewedAnswer.json ``` The command below lists all reviewed answers in a Quick Sight topic. ``` aws quicksight list-topic-reviewed-answers \ --aws-account-id AWSACCOUNTID \ --topic-id TOPICID \ ``` The example below batch deletes up to 100 reviewed answers from a topic. ``` aws quicksight batch-delete-topic-reviewed-answer \ --topic-id TOPICID \ --aws-account-id AWSACCOUNTID \ —answer-ids: ["AnswerId1, AnswerId2…"] ``` You can also batch create topic reviewed answers form a CLI skeleton file with the following command. For more information about CLI skeleton files, see [Using CLI skeleton files](https://docs.aws.amazon.com/quicksight/latest/developerguide/cli-skeletons.html) in the *Amazon Quick Sight Developer Guide*. ``` aws quicksight batch-delete-topic-reviewed-answer \ --cli-input-json file://deleteTopicReviewedAnswer.json ``` To update a reviewed answer, delete the existing answer from the topic with the `batch-delete-topic-reviewed-answer` API. Then, use the `batch-create-topic-reviewed-answer` API to add the updated reviewed answer to the topic. # Working with data stories in Amazon Quick Sight With Generative BI with Quick Sight, authors and readers can generate a first draft of their data story quickly. Use prompts and visuals to produce a draft that incorporates the details that you provide. Data story drafts are not meant to replace your own ideas or to perform analysis. Rather, data stories are a starting point to customize and expand on as needed. The contextual recommendations and suggestions combine your prompt with selected visuals to provide relevant details that are tailored to your data story. For more information about this, see [Generative BI with Quick Sight](quicksight-gen-bi.md). Use the following topics to create, modify, and share a data story. **Topics** + [ # Creating a data story with Generative BI ](working-with-stories-create.md) + [ # Personalize data stories in Amazon Quick Sight ](working-with-stories-personalize.md) + [ # Viewing a generated data story in Amazon Quick Sight ](working-with-stories-view.md) + [ # Editing a generated data story in Amazon Quick Sight ](working-with-stories-edit.md) + [ # Adding themes and animations to a data story in Amazon Quick Sight ](working-with-stories-themes.md) + [ # Sharing a data story in Amazon Quick Sight ](working-with-stories-share.md) # Creating a data story with Generative BI Creating a data story Use the following procedure to create a data story with Generative BI. **To create a data story** 1. Open the [Quick console](https://quicksight.aws.amazon.com/). 1. At left, choose **Stories**. 1. On the **Data stories** page, choose **New Data Story**. 1. In the **Story** screen that appears, navigate to the **Build story** modal and input a data story prompt that you would like to generate. For the best results, don't phrase the prompt like a question. Instead, type the data story that you want Quick Sight to build. For example, say you want to create a data story about the most commonly performed medical procedures by region. A good prompt for this use case is "Build a data story about most commonly performed procedures by physicians in various regions. Also, show the specialties where patients are admitted the most. Recommend where we need to staff more physicians by specialty, and include at least four points of supporting data." You can optionally skip this step and manually create your data story. If you choose to forego entering a prompt, you still need to add a visual to the data story. 1. Under **Select visuals**, choose **Add**. 1. Choose the dashboard that contains the visuals that you want to use, and then choose the visuals that you want. You can add up to 20 visuals to a data story. If you don't see the dashboard that you want to use, use the **Find your dashboards** search bar at the top of the modal. You can choose visuals from any number of dashboards that you have sharing permissions to. Visuals that show a **Restricted** badge have permissions that restrict them from being added to a data story. A visual might be restricted for one of the following reasons: + The dataset is connected to a data source that uses trusted identity propagation with Amazon Redshift. + The dataset is located inside of a restricted folder. 1. (Optional) Use the **Select documents** section to upload up to 5 documents to be used in the data story. Each document can't exceed 10MB. These documents are only used to generate the data story and are not stored in Quick Sight. The following image shows the **Select documents** section of the **Build story** screen. 1. (Optional) If your Quick account is connected to an Amazon Q Business application, check the **Use insights from Amazon Q Business** checkbox to augment your data story with unstructured data sources from Amazon Q Business. For more information about connecting a Quick account to a Amazon Q Business application, see [Augmenting Amazon Quick Sight insights with Amazon Q Business](generative-bi-q-business.md). 1. Choose **Build**. After the data story generates, review the data story and choose from the following options: + **Keep** – Saves the generated content to the canvas. When you choose this option, the **Build story** modal closes and you can start editing your data story. + **Try again** – Allows users to edit the prompt and generate a new data story. + **Discard** – Deletes the generated data story. # Personalize data stories in Amazon Quick Sight User location and job-related information from your IAM Identity Center instance are leveraged to generate personalized data stories that are more relevant to authors and readers. For example, when an author in the US issues the prompt “Write a business strategy focusing on a plan on how to increase the revenue in my location", insights related to the US in the data story's narrative are automatically included. If the author wants the data story to focus on another country such as Canada, they can specify this in the prompt. For personalization to work, you must add country and job title for users in the IAM Identity Center instance that is connected to your Quick account. For more information, see [Add users to your IAM Identity Center directory](https://docs.aws.amazon.com/singlesignon/latest/userguide/addusers.html) in the IAM Identity Center User Guide. User data in your IAM Identity Center instance is connected to your application environment by default. This means that all data stories are personalized by default. You can choose to [opt out of personalization](https://docs.aws.amazon.com/quicksuite/latest/userguide/qs-q-manage-personalization) at any time in the Account settings menu in the QuickSight administration console. **Note** Personalization in data stories is currently available in the US East (N. Virginia) and US West (Oregon) AWS Regions. # Viewing a generated data story in Amazon Quick Sight After you generate and keep a data story, you can access that data story from the **Data stories** page. To view a data story, choose the data story that you want to view to open the story editor. As you create and modify a data story, you can preview how the data story looks to readers. To preview a generated data story, choose the **Preview** icon at the top of the page. To exit the preview, choose **BACK TO EDITOR**. # Editing a generated data story in Amazon Quick Sight After you create and keep a data story, you can modify its content to better fit your needs. You can format data story text, add images, edit visuals, and add new blocks. Stories are made up of different *blocks* that act as containers for text, visuals, and images that you want to include in your data story. Each block can be formatted indepenently from other blocks in the data story, similar to the sections of a pixel perfect report. To format the text of a data story, use the toolbar at the top of the page. The toolbar offers font settings so you can customize the font type, style, color, size, spacing, text highlights, and alignment. You can also use the toolbar to add columns to a data story block. Use one of the following options to add a visual to a data story. + Use the **Visuals** pane to drag and drop a visual into a data story. Only the visuals that you chose when you generated the data story are shown in the **Visuals** pane. You can also choose the **Add** (\$1) icon in the **Visuals** pane to add new visuals that can be dragged and dropped into the data story. Each data story can contain up to 20 visuals. + Choose the data story block that you want to add an image to. When a cursor appears, enter a forward slash (`"/"`) to insert an image or visual to that data story block. To edit a visual in a data story, choose the visual that you want to change, and then choose the **Properties** icon. In the properties pane that appears, you can perform the following actions: + Change, hide, or show the visual's title. By default, the visual title is displayed. + Change, hide, or show the visual's subtitle. By default, the visual subtitle is hidden. + Hide or show data labels. By default, data labels are hidden. + Hide, show, or change the position of the legend. By default, the legend is hidden. To add a new block to a data story, choose the plus (\$1) icon at the bottom of any existing block. Then choose the layout option that you want. You can also move, duplicate, or delete a block from the **Block options** (three dots) icon at the top of each block. To change the layout of items in a block, you can drag and drop the items wherever you want with the six-dot icon next to each item. # Adding themes and animations to a data story in Amazon Quick Sight Themes and animations You can add themes and animations to the stories that you generate. To add a theme or animation to a data story, choose the **Story style** icon. In the **Story style** pane that appears, you can perform the following actions: + For **THEMES**, choose a theme that you think best fits your data story. + For **ANIMATIONS**, choose an animation style and speed. For animation types, you can choose **None**, **Fade**, or **Slide**. The default animation is **None**. For **Speed**, choose **Slow**, **Medium**, or **Fast**. The default speed is **Medium**. # Sharing a data story in Amazon Quick Sight Use the following procedure to share a data story. **To share a data story** 1. In the story editor of the data story that you want to share, choose the **Share** icon at the top right. Alternatively, you can choose the **Share** icon at the top of a data story preview. 1. In the **Share data story** modal that appears, enter the users or groups that you want to share the data story with. 1. (Optional) To save a link for the published data story to your clipboard, choose **Copy Link**. 1. Choose **Publish & Share**. If you try to share a story and receive a message that the story cannot be shared, contact the owner of the dashboard ask them to toggle on the **Allow sharing data stories** switch. For more information about this switch, see [Tutorial: Create an Amazon Quick Sight dashboard](example-create-a-dashboard.md). If you try to share a data story and receive an error message, contact the owner of the dashboard or your Quick account admin for assistance. After you share a data story, users you shared the story with receive a notification email with a link to the story. You can access the data story from the **Data stories** page of their Quick accounts. You can also share the copied link to the data story with users that can access the data story. You can't share a data story that contains restricted data. If you try to share a story that contains restricted data, an error message appears that lists all restricted visuals that are a part of the story. If desired, remove the restricted visuals from your data story before sharing it with users. When you edit a published data story, republish the data story for the changes to propagate to your end users. # Working with scenarios in Amazon Quick Sight Quick users with Admin Pro, Author Pro, or Reader Pro roles can use scenarios to analyze complex business problems with simple natural language. To get started with scenarios, a Quick user describes a problem that they want to solve and adds relevant data from Quick Sight or from their computer to be used in the data analysis. Alternatively, users can let Amazon Q search for all relevant data that can be used to solve the problem. Amazon Q returns a series of analyses or prompts to dive deeper into the data. Users can also enter their own prompts to create a custom analysis. After a new prompt is received, Amazon Q breaks down the analysis into steps and executes them. Outputs include specific data insights, interactive visuals, and an analysis of what the findings might mean for the business with suggested next actions. Scenarios can help Quick Pro users to perform the following tasks: + Automate tedious, error-prone, and inefficient manual data tasks + Modify, extend, or reuse past analyses to quickly adapt to business changes + Dive deeper into data than spreadsheets allow Use the following topics to create and work with scenarios in Amazon Quick Sight. **Topics** + [ ## Considerations for Quick Sight scenarios ](#scenarios-considerations) + [ # Creating an Amazon Quick Sight scenario ](scenarios-create.md) + [ # Working with threads in an Amazon Quick Sight scenario ](scenarios-threads.md) + [ # Working with data in an Amazon Quick Sight scenario ](scenarios-data.md) ## Considerations for Quick Sight scenarios Considerations The following considerations apply to Amazon Quick Sight scenarios. + Amazon Quick Sight scenarios are available to users that have Admin Pro, Author Pro, or Reader Pro roles in Amazon Quick. For information about updating a user to a Quick Pro role, see [Get started with Generative BI](generative-bi-get-started.md). + Scenarios are available in specific AWS Regions listed in [Supported AWS Regions for Amazon Q in Quick](regions.md#regions-aqs). After you review the considerations for Quick Sight scenarios, see [Creating an Amazon Quick Sight scenario](scenarios-create.md) to get started with scenarios in Amazon Quick Sight. # Creating an Amazon Quick Sight scenario Amazon Quick Pro users can create scenarios from Quick Sight dashboards, or from the **Scenarios** section on the Quick Sight home page. Users can create as many scenarios as they need. Each user can have up to 3 active scenarios at a time. Each Quick Sight account supports up to 10 active scenarios at a time. Use the following procedure to create a scenario in Amazon Quick Sight. **Create a new scenario** 1. Open the [Quick console](https://quicksight.aws.amazon.com/). 1. Perform one of the following actions: 1. Open any dashboard, and look for one of the following: + Choose **Analyze this dashboard in a Scenario**, if available, at the top of the dashboard. + From a visual on the dashboard, open the drop-down menu and choose **Explore scenario**. + Choose **Build**, and then choose **Scenario**. 1. On the Quick home page, choose **Scenarios**. On the **Scenarios**, choose **New Scenario**. 1. The new scenario appears. In the text box, describe the problem that you want to solve. This input is the starting point for all of the data pivots and manipulations that will occur in the scenario. The description that you provide can be as broad or as specific as you want, for example "analyze usage trends" or “compute month-over-month and year-over-year changes in usage based on last month's data." 1. Add the data that you want to use in the scenario. You can choose data from Quick Sight dashboards, or you can upload files from your computer. When you choose data from a dashboard, a preview of the selected data is generated for you to review. For more information about previewing and editing data in Quick Sight scenarios, see [Working with data in an Amazon Quick Sight scenario](scenarios-data.md). The following limits apply to the data that is used in a scenario: + You can add up to 10 data sources to a scenario. + Up to 20 visuals can be selected from a dashboard at a time. + Uploaded files must be in `.xlsx` or `.csv` format and can't exceed 1 GB. + Data sources can have up to 200 columns. If you don't add data to the scenario, Amazon Q automatically searches your Quick Sight dashboards to find data related to your problem statement from the previous step. 1. Choose **Start analysis**. When you start an analysis in a Quick Sight scenario, Quick Sight prepares your data for analysis and returns a new *thread*. The thread contains generated prompts that can be used to solve the problem that you described in the scenario. A thread is a turn based contextual conversation that consists of user prompts and Amazon Q responses that you can use to drill down on a specific scenario. You can use threads to write prompts that assume that Amazon Q remembers what was previously discussed in the thread. You can choose a prompt to continue the thread, or you can choose the plus sign (\$1) above the thread to start a new thread. The new thread uses a different prompt than the first thread that you created. For more information about working with threads, see [Working with threads in an Amazon Quick Sight scenario](scenarios-threads.md). # Working with threads in an Amazon Quick Sight scenario After you create a scenario in Quick Sight, the data that Amazon Q generates is presented in *threads* and *blocks*. A thread is a vertical chain of prompts and responses. A block is a single prompt and response pair. Each thread can contain up to 15 blocks, and each scenario can contain up to 50 blocks total across multiple threads. When a new thread is created, a list of Amazon Q-generated prompts appears inside of a new block. When you choose one of the prompts to drill down on, Amazon Q analyzes the data that is relevant to the chosen prompt and returns a summary of all data findings, forecasts, and conclusions that can be drawn from the analysis. To continue the thread and dive deeper into the prompt, choose the plus sign (**\$1**) located below the block to create a new block that contains a new list of generated prompts that factor in the findings from the previous block. To start a new thread that analyzes a different aspect of the data, choose the plus sign (**\$1**) above any block in the scenario to create a new thread. Blocks can be collapsed, duplicated, or deleted from a scenario, as long as the block that you want to change has finished loading. Use the following procedures to make changes to a scenario block. **To collapse, duplicate, or delete a block** 1. Open the [Quick console](https://quicksight.aws.amazon.com/). 1. Choose **Scenarios** from the options pane, and then choose the scenario that you want to change. 1. Navigate to the block that you want to change and choose the ellipsis (…) in the top right of the block. 1. Perform one of the following actions: + To collapse the block, choose **Collapse**. To expand a collapsed block, choose the ellipsis in the top right of the block, and then choose **Expand**. + To duplicate the block, choose **Duplicate**. The block is duplicated and placed in a new thread next to the original block. + To delete the block, choose **Delete**. You can also modify the prompt of a block to better match your use case. Use the following procedure to modify a block prompt. **To modify the prompt of a block** 1. Open the [Quick console](https://quicksight.aws.amazon.com/). 1. Choose **Scenarios** from the options pane, and then choose the scenario that you want to change. 1. Navigate to the block that you want to change and choose **Modify block**. 1. In the **Modify block** popup that appears, enter a new description for the block, and then choose **Apply**. After you modify a prompt, Amazon Q analyzes the data and returns a new generated analysis that reflects the changes that were made to the prompt. # Working with data in an Amazon Quick Sight scenario When you create a scenario in Amazon Quick Sight, you can preview and modify the data that the scenario uses to generate summaries. Use the following sections to learn about the ways Quick users can interact with data in a scenario. **Topics** + [ ## Adding more data to a scenario ](#scenarios-data-add-data) + [ ## Editing data in a preview ](#scenarios-data-edit-preview) + [ ## Editing data in a snapshot ](#scenarios-data-edit-snapshot) ## Adding more data to a scenario After you create a scenario in Amazon Quick Sight, you can add more data to the scenario at any time. Use the following procedure to add data to an Amazon Quick Sight scenario. **To add data to an existing Amazon Quick Sight scenario** 1. Open the [Quick console](https://quicksight.aws.amazon.com/). 1. Choose **Scenarios** from the options pane, and then choose the scenario that you want to add more data to. 1. Choose the **Data Source** icon in the actions bar to open the **Data** pane. 1. Perform one of the following actions: 1. To add Quick Sight data to the scenario, choose **Find Data**, and then choose the dataset or dashboard visuals that you want to add to the scenario. After you have selected all of the Quick Sight data that you want to add to the scenario, choose **Add**. 1. To upload a file from your computer to the scenario, choose **Upload File**. The following limits apply to the data that is added to a scenario: + You can add up to 10 data sources to a scenario. + Up to 20 visuals can be selected from a dashboard at a time. + Uploaded files must be in `.xlsx` or `.csv` format and can't exceed 1 GB. + Data sources can have up to 200 columns. After you add new data to a scenario, Amazon Q includes the data in all new analyses. ## Editing data in a preview When you choose data from a Quick Sight dashboard to be used in a scenario, a preview of the data is generated for review before it's added to the analysis. If needed, the following changes can be made to dashboard data in the preview state: + **Filters** – If you only want to analyze a subset of the available data or if you need to reduce the number of rows that are included in the scenario, you can apply filters to the data. + **Sort** – If the available data exceeds 1 million rows and you want to prioritize the retention of the values in a specific column, you can sort the data to fit your needs. ## Editing data in a snapshot When you add dashboard or external data to a scenario, Quick Sight creates a snapshot of the data sources to be reviewed. To see a snapshot of the data used in a scenario, choose the **Data Source** icon in the actions bar. This opens the **Data** pane, and then you can choose the data snapshot that you want to review. You can perform the following actions on a data snapshot: + To update the title of the data snapshot, choose the pencil icon next to the title and enter a new title for the snapshot. + Choose the **Filter** icon to filter the data that is used in the scenario. This option can be used if you want the scenario to only use a subset of the data that is added to the scenario. + Choose the **Sort** icon to sort the data that is used in the scenario. This option can be used to prioritize the retention of specific columns if the data exceeds 1 million rows. + Choose the **Fields list** icon to choose which fields are included in the scenario. This option can be used to control which columns are used in the scenario. When you are finished updating the scenario data, close the **Data** pane.