Sign inGet started

Livedocs AI

Flexible AI assistant for data work with chat sessions, agent modes, and model choice

Livedocs AI

Livedocs AI is a highly flexible way to use AI for data work.

Unlike a typical chat-based assistant, Livedocs AI shows the work — you see the generated queries, code, and transformations, not just an opaque answer you have to trust. You also get to pick your own model — we don’t lock you in.

Chat Sessions & Tagging

Livedocs AI works through chat sessions. You can:

  • Manually tag cells, dataframes, tables, files, and more into the chat.
  • Drop files into the chat prompt box.

AI Modes

  1. Agent – End-to-end AI. Has access to the terminal, the notebook, all cells, files, and data sources. It won’t stop until the task is done.
  2. Fix – Edits specific Python or SQL cells to fix issues.
  3. Explain – Describes what a cell or piece of code does without modifying it.

What You Can Do with Livedocs AI

1. Fix Errors in Code or Queries

  • When you hit a Python error or a SQL error, you’ll see a “Fix with assistant” button in the stack trace.
  • In the Problems section, click the bulb icon on specific errors or warnings to have AI fix them.

2. Explain Cell Content

  • Great for onboarding or understanding unfamiliar code.
  • Example: “Explain this SQL query that calculates monthly churn rate.”

3. Agent Mode

  • Give AI a broad, end-to-end task.
  • Examples:
    • Build and train a model from a dataset.
    • Explore a large file and uncover insights.
    • Fetch and process external datasets.
  • Agents can browse the web for datasets or documentation.
  • You can define Rules in Workspace Settings (coming soon) — custom instructions for Agent behavior that help maintain coding standards, enforce patterns, and personalize assistance.

Pricing

  • Every plan gets $10 of free AI usage across any model.
  • Paid plans can set higher limits and pay-as-you-go.

MCP Server Integration (Coming Soon)

Livedocs will soon support MCP servers — connecting directly to external systems and data sources through the MCP protocol.

Instead of explaining your data structure repeatedly, MCP lets Livedocs integrate directly with your tools.

  • MCP servers expose capabilities via the protocol, connecting Livedocs to external APIs, databases, or services.
  • You’ll be able to configure custom MCP servers via a JSON file in Workspace Settings.

Security Best Practices for MCP

  • Verify the source – Only install MCP servers from trusted developers and repositories.
  • Review permissions – Check what data and APIs the server will access.
  • Limit API keys – Use restricted API keys with minimal required permissions.
  • Audit code – For critical integrations, review the server’s source code.