About dbt Wizard

Your personal dbt agent — wherever you work.

dbt Wizard is an AI agent purpose-built for governed data development in dbt. Unlike general-purpose coding agents, it understands your dbt project through a native metadata engine — a structured index of lineage, model health, tests, contracts, run results, and semantic definitions.

Think of it like a map of your city: dbt Wizard knows how everything connects before it starts, rather than walking every street to figure out the layout.

dbt Wizard comes with the following capabilities:

• Project understanding: A native dbt metadata engine for lineage, contracts, tests, and runtime context
• Impact awareness: Checks upstream and downstream dependencies before you change code
• Safe validation: Compiles and builds changes before review
• Complete workflow: Investigate, change, validate, and review in one place
• Setup and governance: Works out of the box with dbt governance built in

Share your feedback!

We'd love to hear how dbt Wizard is working for you. Share your feedback by either running the /feedback slash command in your interactive terminal session or by going to the #dbt-wizard channel in the dbt Community Slack.

Thanks so much for your help in improving dbt Wizard and dbt data development!

Use dbt Wizard

dbt Wizard is available in:

• dbt platform: Use managed AI provider keys or bring your own key (BYOK) credentials for a supported provider. Available in public preview for Studio IDE and in public beta for the dbt Wizard home tab.
• Terminal (public beta): Use BYOK credentials for a supported provider.

For more info on pricing, refer to the Billing page.

dbt Wizard is data warehouse agnostic and works with both the dbt Fusion engine and dbt Core — no specific engine is required.

Supported AI providers

dbt Wizard

dbt Wizard supports different AI providers depending on where you use it.

Provider	dbt Wizard in dbt platform	dbt Wizard CLI
OpenAI	✓ (managed or BYOK)	✓ (OpenAI subscription or BYOK)
Anthropic	✓ (BYOK)	✓ (BYOK)
Azure AI Foundry / Azure OpenAI	✓ (BYOK)	✓ (BYOK)
AWS Bedrock	-	✓ (BYOK)
Snowflake Cortex	-	✓ (BYOK)

• Configure dbt platform integrations in account settings. BYOK is available for Enterprise and Enterprise+ plans.
• Configure BYOK for the CLI. For OpenAI subscription support in the CLI, run wizard providers configure openai_subscription and follow the prompts.

Get started with dbt Wizard

Terminal Beta

Available in public beta.

A terminal-based agent for governed data development in dbt, whether your team uses the dbt platform or self-hosts. Bring your own key to experience the full agentic analytics engineering loop.

New to the terminal?

If you've never used the terminal before, check out the terminal guide. Some tips include:

• Enter / to see the available commands or try out /overview to get a quick summary of your project.
• Press Shift+Tab to cycle through collaboration modes.

Install dbt Wizard as wizard on your PATH using the curl script for your operating system:

macOS/Linux

curl -fsSL https://public.cdn.getdbt.com/dbt-wizard/install/install-wizard.sh | sh

Windows

Run the following in PowerShell:

irm https://public.cdn.getdbt.com/dbt-wizard/install/install-wizard.ps1 | iex

Then verify the install and start a session:

wizard --version   # confirm the install
wizard             # start an interactive session

After running wizard --version, you should see something like dbt-wizard VERSION. Run wizard --help to see all available commands and flags. dbt Wizard installs default config files — refer to the config reference for more details.

dbt Wizard CLI in your terminal

dbt platform Preview

Available in public preview.

Leverage agentic capabilities in the home app or Studio IDE for governed data development in dbt.

To get started:

1. Make sure an admin has enabled dbt Wizard.
2. Navigate to the dbt Wizard icon in the left sidebar of the dbt platform.
3. Open a project in Studio IDE or the home app.
4. Try a prompt, such as:
   • summarize what this project does
   • list all models with no tests
   • add not_null and unique tests to the primary key of stg_customers

Refer to Use cases and examples for more prompts.

dbt Wizard in the dbt platform

(Be warned, the wizard has been known to

.)

Next steps

Now that you know where to start, continue with the Quickstart for prerequisites, authentication, prompt examples, and additional commands.

dbt Wizard is in public preview as an AI agent layer across the managed dbt platform. Some customers may still have access to dbt Copilot until the updated AI agent layer is generally available. Contact dbt Support with any questions.

Related docs

• dbt Wizard in Studio IDE — generate docs, tests, semantic models, SQL, and delegate end-to-end model work
• Skills — give dbt Wizard reusable instructions for your project
• Migrate to dbt Wizard — switch from Claude Code, Cursor, or another AI agent to dbt Wizard
• dbt MCP server — bring dbt context into any MCP-compatible AI tool

Was this page helpful?

Privacy policyCreate a GitHub issue

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.