Skip to main content
Public Preview The Wherobots VS Code Extension provides Jupyter integration that connects your local notebooks to remote Wherobots compute with automatic kernel selection, all within your editor. You describe an analysis in your editor’s chat, and the AI assistant writes and runs the notebook cells, using the Wherobots MCP Server to find datasets and table schemas.
The steps below use GitHub Copilot Chat in VS Code. Other editors have an equivalent feature — Cursor (Chat / Composer), Windsurf (Cascade), Kiro (AI Chat), Positron (Copilot Chat), Trae (Side chat).Consult your editor’s documentation for details on accessing chat, switching modes, and selecting models.

​
Before you start

Ensure you have the following:
  • The Wherobots VS Code Extension installed and configured (also compatible with Cursor, Windsurf, Kiro, and other editors)
  • A Wherobots Account. For more information, see Create a Wherobots Account.
  • An active GitHub Copilot subscription (or your editor’s equivalent AI assistant). For more information about Copilot, see Microsoft’s GitHub Copilot.
    Use advanced modelsAI-assisted notebook generation works best with the latest advanced AI models (for example, the latest Claude Opus, Gemini Pro, or GPT Codex models) — ensure your subscription includes access to these models for optimal results.

​
Create and run a notebook with your AI assistant

To create and run a Jupyter notebook connected to Wherobots compute using your editor’s AI assistant:
1

Open the Command Palette

To open the Command Palette, click the search bar at the top of your editor and type >wherobots:.Command Palette
You can also press ⌘ + Shift + P on Mac, Ctrl + Shift + P on Windows/Linux to open the Command Palette.
2

Sign in to Wherobots

If you haven’t already, sign in to Wherobots Cloud:
  1. Type Wherobots: Sign In and click Enter.
  2. A browser window opens for you to sign in to Wherobots and select your Organization; when you’re done, return to your editor.
Sign in to Wherobots
Prefer an API key? Type Wherobots: Set API Key and enter your Wherobots API key when prompted. If you haven’t created an API key yet, run Wherobots: Generate API Key on Wherobots Cloud to create one.
3

Create a workspace

Open the Command Palette and type Wherobots: Create Workspace.Click Enter to run the command.
4

Choose a runtime

  1. Choose the runtime configuration for your workspace, including Region, Runtime Size, and Idle Timeout.
  2. Click Create & Start.
Create Workspace runtime configuration
You can select from additional compute tiers. A trial Organization without a payment method can use the Tiny, Micro, and Small runtimes.
5

Open the chat panel

Open your editor’s AI assistant. In VS Code, open GitHub Copilot Chat via View > Chat.
In VS Code, you can also open Copilot Chat by pressing ⌘ + Shift + I on macOS or Ctrl + Shift + I on Windows/Linux. Other editors have their own shortcuts — consult your editor’s documentation.
6

Select Agent mode

Select Agent mode from the chat mode dropdown at the top of the chat panel.
Select Agent mode in Copilot Chat

Selecting Agent mode in Copilot Chat in VS Code. Consult the documentation for your chosen editor on how to change modes and models.

7

Choose a high-performance model

Select a high-performance AI model for optimal results. This includes the latest versions of advanced models such as Gemini Pro, Claude Opus, Claude Sonnet, or GPT Codex.
8

Confirm the MCP server is connected

Ask a simple question to confirm the MCP server is connected:
List the available tables in wherobots_pro_data.
Shortly, you should see a response listing available tables in the wherobots_pro_data dataset.If no SQL session is running, the next SQL query you run through the MCP server starts one, and a cold SQL session can take several minutes to start. While it starts, submit_read_query returns a query_id, and your AI assistant calls get_query_results with that ID until the query finishes and the rows come back. See How queries run.
9

Prompt the AI assistant to build your notebook

Enter a natural language prompt describing the notebook you want. For example:
Create a notebook that finds all parks within 1 mile of subway stations in Manhattan using the Overture Maps dataset. Run each cell.
When your editor requests permissions for the Wherobots MCP server, click Allow (or Allow in this session to avoid repeated prompts).
At this point, the AI assistant will locally generate a notebook (an .ipynb file) based on your prompt. You can open and run this notebook in your editor.

​
Run a local notebook against Wherobots compute

Now that your notebook is generated from the previous step, you can run it and see the results of each cell directly within your editor.
You can use these steps to run any local Jupyter notebook against Wherobots compute, not just AI-generated notebooks. This allows you to leverage Wherobots compute and datasets in your existing notebooks as well.
1

Open the Command Palette

To open the Command Palette, click the search bar at the top of your editor and type >wherobots:.Command Palette
You can also press ⌘ + Shift + P on Mac, Ctrl + Shift + P on Windows/Linux to open the Command Palette.
2

Open the Workspaces view

Click Wherobots: Focus on Workspaces View.Command Palette
3

Create a workspace

Click Create WorkspaceCreate Workspace buttonCreating a workspace provisions a runtime — a dedicated compute cluster — in Wherobots Cloud. Once the runtime is running, your local notebook can connect to it and execute code remotely.
4

Open the local notebook

If the notebook is already open in your editor, skip to the next step.Otherwise, do the following:
  1. Hover over the running workspace you started and a plug icon () will appear.
  2. Click the plug icon to find and open the notebook file on your local machine. The notebook will open in a new tab in your editor.
Plug icon
5

Run all cells

Within the notebook, click Run All to execute all cells.Local notebook workflow
6

Select kernel source

When prompted for the kernel source, select Wherobots.
7

Select a running workspace

Select a running workspace from the list. Each workspace corresponds to a runtime provisioned in Wherobots Cloud.
8

Choose the Jupyter kernel

Select the appropriate Jupyter kernel. For most workflows, choose Python 3 (ipykernel).

​
Effective prompting strategies

The quality of AI-generated notebooks depends heavily on the prompts you provide. Use the following strategies for best results:
AI-assisted development is meant to be iterative. You may need to refine your prompts or guide the AI assistant through multi-step analyses. The experience improves as you develop prompting patterns that work well with your datasets.

​
Model selection tips

Use advanced AI models like the latest versions of the following for optimal results with AI-assisted notebook development:
  • Claude Sonnet
  • Claude Opus
  • Gemini Pro
  • GPT Codex
These models have enhanced reasoning capabilities and better contextual understanding, making them more effective at generating accurate code and handling complex notebook creation tasks.

​
Next steps

Browse Your Data

Browse catalogs, schemas, and tables in the Data Hub sidebar. Create notebooks from your data with AI.

Submit Job Runs

Submit Python scripts as Wherobots job runs.

Workspaces & Usage

Create, start, stop, and destroy notebook workspaces.