docs: Semantic Catalog and AI assistant (#8388)

Author: mjirv

docs/pages/product/workspace.mdx

@@ -13,35 +13,38 @@ and are only available in Cube Cloud.
 ## Workspace tools in Cube Cloud
 
 In Cube Cloud, you can:
-* Use the [data model editor][ref-data-model] with the [development
-mode][ref-dev-mode] and [Rollup Designer][ref-rollup-designer] to build
-the data model of your semantic layer.
-* Use [SQL Runner][ref-sql-runner] to inform the development of the data
-model.
-* Use [Playground][ref-playground] to run queries and test the data model.
-* Use [Chart Prototyping][ref-vizard] to generate code of a front-end
-application that works with Cube.
-* Use [Semantic Layer Sync][ref-sls] to connect your semantic layer to BI
-tools.
-* Use [Query History][ref-query-history] to observe queries and their
-performance in real-time.
-* Use the [pre-aggregations page][ref-pre-aggs] to inspect pre-aggregations
-and their build history.
-* Use [Performance Insights][ref-perf-insights] to analyze the performance
-of your deployment as a whole.
-* Use the [access control page][ref-access-control] to manage users of your
-Cube Cloud account and [single sign-on][ref-sso].
-* Use [Budgets][ref-budgets] to control the usage and spend of your Cube
-Cloud account.
-* Use [Preferences][ref-prefs] to adjust the workspace to your liking.
+
+- Use the [data model editor][ref-data-model] with the [development
+  mode][ref-dev-mode] and [Rollup Designer][ref-rollup-designer] to build
+  the data model of your semantic layer.
+- Use [SQL Runner][ref-sql-runner] to inform the development of the data
+  model.
+- Use [Playground][ref-playground] to run queries and test the data model.
+- Use [Chart Prototyping][ref-vizard] to generate code of a front-end
+  application that works with Cube.
+- Use [Semantic Layer Sync][ref-sls] to connect your semantic layer to BI
+  tools.
+- Use [Query History][ref-query-history] to observe queries and their
+  performance in real-time.
+- Use the [pre-aggregations page][ref-pre-aggs] to inspect pre-aggregations
+  and their build history.
+- Use [Performance Insights][ref-perf-insights] to analyze the performance
+  of your deployment as a whole.
+- Use the [access control page][ref-access-control] to manage users of your
+  Cube Cloud account and [single sign-on][ref-sso].
+- Use [Budgets][ref-budgets] to control the usage and spend of your Cube
+  Cloud account.
+- Use [Preferences][ref-prefs] to adjust the workspace to your liking.
+- Use [AI Assistant][ref-ai-assistant] to explore and query data with natural language.
+- Use [Semantic Catalog][ref-semantic-catalog] to search a unified view of connected data assets, see lineage, and explore connected BI content.
 
 ## Workspace tools in Cube Core
 
 With Cube Core, you can:
 
-* Use the data model builder to generate the initial data model.
-* Use [Playground][ref-playground] to run queries and test the data model.
-* Use the [command-line tool][ref-cli] to automate your workflows.
+- Use the data model builder to generate the initial data model.
+- Use [Playground][ref-playground] to run queries and test the data model.
+- Use the [command-line tool][ref-cli] to automate your workflows.
 
 [ref-infrastructure]: /product/deployment/cloud
 [ref-data-model]: /product/workspace/data-model
@@ -59,3 +62,5 @@ With Cube Core, you can:
 [ref-budgets]: /product/workspace/budgets
 [ref-prefs]: /product/workspace/preferences
 [ref-cli]: /product/workspace/cli
+[ref-ai-assistant]: /product/workspace/ai-assistant
+[ref-semantic-catalog]: /product/workspace/semantic-catalog

docs/pages/product/workspace/_meta.js

@@ -1,17 +1,18 @@
 module.exports = {
-  "playground": "Playground",
+  playground: "Playground",
   "data-model": "Data Model",
   "rollup-designer": "Rollup Designer",
   "dev-mode": "Development mode",
-  "vizard": "Chart Prototyping",
+  vizard: "Chart Prototyping",
   "semantic-layer-sync": "Semantic Layer Sync",
   "sql-runner": "SQL Runner",
   "query-history": "Query History",
   "pre-aggregations": "Pre-Aggregations",
-  "performance": "Performance Insights",
+  performance: "Performance Insights",
   "access-control": "Access Control",
-  "sso": "Single Sign-on",
-  "budgets": "Budgets",
-  "preferences": "Preferences",
-  "cli": "CLI"
-}
+  sso: "Single Sign-on",
+  budgets: "Budgets",
+  preferences: "Preferences",
+  cli: "CLI",
+  "ai-assistant": "AI Assistant",
+};

docs/pages/product/workspace/ai-assistant.mdx

@@ -0,0 +1,85 @@
+# AI Assistant
+
+Business users can ask questions about your organization's Cube data model and run queries using natural language.
+AI Assistant is integrated with the [Playground][ref-playground] and [Semantic Catalog][ref-catalog] so that users can easily explore their results further.
+
+<SuccessBox>
+
+AI Assistant is available in Cube Cloud on
+[Premium and above](https://cube.dev/pricing) tiers.
+[Contact us](https://cube.dev/contact) for details.
+
+</SuccessBox>
+
+<Screenshot src="https://ucarecdn.com/9aee5273-e219-4ccc-aa5c-2c8b66a6c932/assistant.jpg" />
+
+## Getting Started
+
+AI Assistant is currently in preview. To get started, please ask your account team to enable AI Assistant for you.
+
+Then, if you've already set up Semantic Catalog, you're ready to use AI Assistant. If you haven't, do the following to enable AI Asisstant:
+
+1. In your Cube deployment sidebar, navigate to "Settings" and then "Catalog Services"
+2. Click the button to enable the Catalog. This will connect your Cube data model and enable AI Assistant.
+3. If you'd like to connect any downstream business intelligence tools, follow the [guide on the Semantic Catalog page][ref-catalog-downstream].
+
+## Using AI Assistant
+
+Users can ask questions and have conversations with the AI Assistant to better understand the data in your Cube data model, to pull data, and run basic analyses.
+There are two specific types of questions that the AI Assistant can answer: catalog questions and data queries. These are described in more detail below.
+
+### Catalog questions
+
+A catalog question is a question about what data is available to the user or what particular data assets mean (for example, a dimension or measure).
+
+**Example**
+
+A user might want to do some analysis around geographies, but they're not sure if their organization already has dashboards about users' locations
+or how granular their organization's data on user locations goes. They could ask:
+
+> What info do we have about user locations?
+
+The AI Assistant will reply with a summary and display the dashboards, charts, and/or Cube view(s) containing location information for the user to explore.
+
+<Screenshot src="https://ucarecdn.com/0fb3768f-1b1a-42d5-89f0-38555b0c7427/Screenshot20240624at41011PM.png" />
+
+### Data Queries
+
+A data query is one where the user wants the AI Assistant to generate and run a Cube query, and return the results.
+Users can get quick answers to questions instead of having to ask an analyst, file a ticket, or navigate a complex visualization tool.
+
+**Example**
+
+A sales analyst might want to know which cities orders are trending in lately. They could ask the following question:
+
+> Where did we have the most orders last month?
+
+The query will automatically run in the sidebar and can be opened in the [Playground][ref-playground] for further exploration.
+
+<Screenshot src="https://ucarecdn.com/4249ff1e-fae1-42c8-ad3a-b9e406ea2022/Screenshot20240624at34327PM.png" />
+
+## FAQ and limitations
+
+### 1. What language model(s) does the AI Assistant use?
+
+- The AI Assistant currently uses GPT-4o from OpenAI, but this may change in the future
+
+### 2. Are conversations saved or used for training models?
+
+- Per our terms with the LLM provider(s), they do not use the conversations for training models.
+- They may save conversations for up to 30 days for abuse and fraud monitoring purposes.
+- Note that customer data (i.e. the results of queries) is _never_ visible to the LLM in the AI Assistant.
+
+### 3. Can the LLM hallucinate or give incorrect results?
+
+- We make every effort to avoid hallucinations and incorrect results. However, the nature of AI-based systems is that they may make mistakes from time to time.
+- If the model hallucinates data assets (such as dimensions, measures, or views) that don't exist, the user will see an error in the playground. It will _never_ return "fake" data, as a valid Cube query is needed to display results.
+
+### 4. How can I give feedback or train the model?
+
+- To give feedback to the model, use the thumbs-up and thumbs-down buttons that appear under each response.
+- If a model is consistently getting something wrong, it may be a sign that the data model is confusing or incomplete. Check things like field labels and descriptions and make sure that irrelevant fields are not marked as visible in your Cube data model.
+
+[ref-catalog]: /product/workspace/semantic-catalog
+[ref-playground]: /product/workspace/playground
+[ref-catalog-downstream]: /product/workspace/semantic-catalog#connecting-downstream-tools

docs/pages/product/workspace/semantic-catalog.mdx

@@ -0,0 +1,59 @@
+# Semantic Catalog
+
+Semantic Catalog lets users search, understand, and re-use trusted data products,
+both from Cube and external sources such as cloud data warehouses and business intelligence tools.
+
+<SuccessBox>
+
+Semantic Catalog is available in Cube Cloud on
+[Premium and above](https://cube.dev/pricing) tiers.
+[Contact us](https://cube.dev/contact) for details.
+
+</SuccessBox>
+
+<Screenshot src="https://ucarecdn.com/d8e09149-7ed2-4f5c-83f6-406734557efb/catalog.jpg" />
+
+## Getting Started
+
+### Enabling Semantic Catalog
+
+Semantic Catalog is currently in preview. First, ask your account team to enable it for you.
+
+Then, in your Cube deployment, navigate to the "Catalog" sidebar tab.
+If it is not already enabled, there will be a button to get started.
+After you click this button, your Cube data model will sync to the Semantic Catalog.
+In a few moments, you will see Cubes, Views, and Tables appear in the Semantic Catalog.
+
+### Connecting downstream tools
+
+In addition to your Cube data model, Semantic Catalog can be used to understand charts and dashboards in downstream business intelligence and data visualization tools.
+These currently include:
+
+- [Tableau][ref-tableau]
+- [Superset][ref-superset]
+- [Preset][ref-superset]
+- Amazon Quicksight
+
+To connect these, navigate to "Settings" in your Cube deployment sidebar, and then choose "Catalog Services."
+Click the "Add Service" button, and a modal will pop up for you to enter credentials, test the connection, and create your service.
+
+<Screenshot src="https://ucarecdn.com/a060a3cb-f5f0-4b5e-90fb-84694d6c32f4/Screenshot20240624at43731PM.png" />
+
+## Usage
+
+### Overview
+
+You can search and filter for data assets such as Cubes, Views, tables, charts, and dashboards.
+Semantic Catalog will show you an overview of each data asset, including information such as name,
+description, the measures and dimensions included (for a Cube or View), and usage information.
+
+### Lineage
+
+Semantic Catalog can be used to explore lineage between your connected data assets.
+For example, for a View, users can see what tables and Cubes flow into it as well as the downstream
+dashboards that query it in tools such as Tableau and Superset.
+
+<Screenshot src="https://ucarecdn.com/9adbeb24-203d-4608-9351-fac348a01f51/Screenshot20240624at44511PM.png" />
+
+[ref-tableau]: /product/configuration/visualization-tools/tableau
+[ref-superset]: /product/configuration/visualization-tools/superset