Skip to main content
The Wherobots VS Code extension provides Jupyter integration that connects your local notebooks to remote Wherobots compute with automatic kernel selection all within VS Code.
  1. Install the Wherobots VS Code extension and set your API key via Wherobots: Set API Key.
  2. Run Wherobots: Create Workspace from the Command Palette and click Create & Start.
  3. Open GitHub Copilot Chat in Agent mode.
  4. Prompt Copilot to build and run your notebook, e.g.:
    Create a notebook that finds all parks within 1 mile of subway stations in Manhattan using Overture Maps. Run each cell.
  5. Allow the Wherobots MCP server when prompted.

​
Benefits of AI-assisted notebook development

AI-assisted notebook development with the Wherobots VS Code extension and GitHub Copilot Chat offers several key benefits:
Generate code, data loading, and analysis steps with natural language prompts.Work within VS Code without needing to switch contexts between different tools for notebook development and Wherobots interaction.
Focus on analysis and insights while Copilot handles code generation and execution details.
Explore datasets and analysis techniques with AI guidance, making it easier to get started with new data or methods.
Leverage the Wherobots MCP server for dataset discovery and execution, unlocking the full potential of Wherobots Cloud in your notebooks and then turn those notebooks into repeatable workflows and jobs.

​
Before you start

Ensure you have the following:
  • The Wherobots VS Code Extension installed and configured
  • GitHub Copilot installed
    Use advanced modelsAI-assisted notebook generation works best with the latest advanced AI models available in Copilot (for example, the most capable Claude, Gemini, or GPT models) — ensure your Copilot subscription includes access to these models for optimal results.

​
Create and run a notebook with Copilot

Follow these steps to create and run a Jupyter notebook connected to Wherobots compute using GitHub Copilot Chat:
1

Set your API key

If you haven’t already, click View > Command Palette and run Wherobots: Set API Key to enter your Wherobots API key.
If you haven’t created an API key yet, enter Wherobots: Generate API Key on Wherobots Cloud to create an API key.
2

Create a workspace

In the VS Code command palette, enter Wherobots: Create Workspace.Use the defaults or select the desired runtime configuration for your workspace.Click Create & Start.A pop-up in the lower right corner of VS Code will say your workspace is starting.Create Workspace
3

Open Copilot Chat in Agent mode

Open GitHub Copilot Chat (View > Chat from the menu bar) and select Agent mode from the chat mode dropdown at the top of the chat panel.Select Agent mode in Copilot Chat
4

Warm up the MCP server

Before diving into complex prompts, send a simple question to warm up the MCP server connection:
List the available tables in wherobots_pro_data.
This confirms the MCP server is responding and helps Copilot discover available datasets before you start building your notebook.
5

Prompt Copilot 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.
Copilot will use the Wherobots MCP server to discover datasets, generate code cells, and execute them against the connected Wherobots kernel.
When Copilot requests permissions for the Wherobots MCP server, click Allow (or select Allow in this session to avoid repeated prompts).

​
Effective prompting strategies

The quality of AI-generated notebooks depends heavily on the prompts you provide. Use the following strategies for best results:
StrategyExample prompt
Be specific about the dataset”Use the Overture Maps buildings dataset to find all hospitals in Chicago”
Request validation”Check that each query works at a small scale before adding it to the notebook”
Request iteration on failures”If a query fails, debug and fix it, then try again”
Specify output format”Display the results on a map”
Use advanced AI models like Claude Sonnet 4.6, Claude Opus 4.6, Gemini 3.1 Pro, or GPT-5.3 Codex (as of March 2026) for optimal results with AI-assisted notebook development.
AI-assisted development is iterative. You may need to refine your prompts or guide Copilot through multi-step analyses. The experience improves as you develop prompting patterns that work well with your datasets.

​
Run a local notebook against Wherobots compute

If you have an existing notebook that you want to execute against Wherobots compute, follow these steps to connect it to a running workspace:
1

Open the Command Palette

Open the Command Palette (⌘ + Shift + P on Mac, Ctrl + Shift + P on Windows/Linux).
2

Open the Wherobots sidebar

Navigate to the Wherobots sidebar by running Wherobots: Focus on Workspaces View.
3

Create a workspace

Create a new workspace with the desired runtime configuration.
4

Initiate kernel connection

Click the plug icon () in the sidebar to initiate the kernel connection.
5

Open your notebook

Click Open Notebook and select the .ipynb file on your local machine that you want to connect to Wherobots compute.
6

Run all cells

Within the notebook, click Run All to execute all cells.
7

Select kernel source

When prompted for the kernel source, select Wherobots.
8

Select a running workspace

Select a running workspace from the list of available runtimes.
9

Choose the Jupyter kernel

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