Studio Assistant (Private Preview)

The assistant is an AI first interface for end-to-end analytics creation, from data acquisition to data modeling, insights generation, and embedding. The assistant is available for managed cloud customers, as well as self-hosted customers (as long as the prerequisites are met). Only users with at least Data Designer permissions have access to this feature.

Note:

The assistant is currently in private preview and is available for select customers. Some of its capabilities are still experimental and should be treated as such.

In order to succeed, please use simple data models that follow the best practices for optimizing your data model for AI.

The studio assistant is an extension to the analytics assistant which is currently GA. The two features will grow together to become a single assistant which is exposed across the product to assist with different use cases.

Supported LLMs

To use the assistant, you must first configure and deploy an LLM provider, such as OpenAI or Azure OpenAI Service. See Setting Up Your LLM for instructions.

Enabling the Assistant

In order to use the assistant, it must be enabled by an Admin, in the Admin tab, under App Configuration > Sisense Intelligence. This makes the assistant available via the Assistant tab (at the top of the Sisense window) to all Data Designers across the environment.

Using the Assistant

To use the assistant, open the Assistant tab.

In the assistant, you can:

  • Type your question in natural language

  • Choose from suggested questions

  • Create a new chat session and navigate between sessions

  • Upload a file (pdf or image) for additional context (experimental)

Tip:

The assistant is not yet ready to handle complex data models. In order to succeed, choose a well defined data model.

The following tables depicts what you can do with the assistant:

 

Created by the assistant

Display/Edit from Fusion

Actions

Data Model

Create a data model with synthetic data

N/A

Save and build

Chart

Create and

Modify chart attributes

N/A

Get embed code

Dashboard

Create  and Modify  a Dashboard*

Display and Modify (only if generated by the assistant)

Get embed code

* Note that the assistant respects data governance rules defined in the product, and therefore you can only create dashboards on data sources with the appropriate permissions (can `use` or `edit`).

Creating Data Models from the Assistant

You can ask the assistant to create a data model:

  1. For example, in the Assistant tab, type “Create an Ecommerce data model” and press Enter.

    The data model is generated and the tables to be included are displayed.

  2. Review the tables to be included. Either manually or conversationally, you can add additional tables, edit the existing tables, or leave everything as-is.

    Note:

    The synthetic data (generated data, not real-world data) may hold content that does not match the semantic meaning of the column. This functionality provides the user with a quick way to prototype and design the data model and visualization, without paying attention to the data insights.

  3. When you are ready, click Create Data Model to build the data model into an ElastiCube. When the process is complete, a “Data generated successfully” message is displayed.

  4. Click the Data tab and select your newly created data model to review the complete structure.

Creating, Displaying, and Modifying Dashboards from the Assistant

Note:

For the preview, you can only display and use dashboards that were created via the assistant. This is a precautionary measure, to ensure that there are no undesired effects on existing dashboards. In an upcoming release, you will be able to display and use all dashboards from the assistant.

When creating a new dashboard via the assistant, it is saved automatically. It can then be displayed and modified later, under the Analytics tab, with all other dashboards.

You can use the assistant to create a dashboard for you, either from a pre-existing data model, or even from the data model that you created using the assistant.

  1. For example (after creating a data model as described above), in the Assistant tab, type “Create a dashboard based on this data model” and press Enter.

    You may be requested to select which data source to use. The assistant then generates the requested dashboard.

  2. You can now view the dashboard in the Analytics tab. Click the link that the assistant provides to open the dashboard in the Analytics tab.

  3. Click to customize any widget in the Widget Editor, just as you would for any dashboard.