AI agents

Lightdash AI agents transform the way you interact with your data by allowing you to ask questions in natural language and get meaningful insights back. Currently, you can interact with AI agents in Slack or the Lightdash app, with more options coming soon.

​

How it works

Ask questions about your data, and it will:

• Automatically select the most relevant data model and metrics to answer your question
• Build and execute queries with appropriate dimensions, filters, and limits
• Present results in the most insightful format, whether that’s a visualization, table, or natural language summary
• Ask clarifying questions when needed to ensure you get exactly what you’re looking for

​

Preparing your data for AI

To get the most accurate answers, it’s important to properly prepare your dimensions and metrics. The quality of the results depend on the quality of your metadata and documentation.

Watch a demo below, or keep scrolling for more details.

​

Documenting your data

Good documentation is crucial for AI to understand your data models and provide meaningful insights. Here are some key tips:

• Write clear, descriptive names for metrics and dimensions that avoid acronyms or technical jargon
• Add detailed descriptions to all metrics and dimensions explaining what they represent.
• Descriptions can even include example questions that AI could answer with the metric (e.g. “Useful for answering questions like ‘What is the total revenue for the USA?’”).
• Use business terminology that would make sense to any user, not just technical teams
• Include units of measurement where applicable (e.g. “Revenue in USD” rather than just “Revenue”)
• Document any important caveats or limitations about the data

Remember: If your colleague wouldn’t understand your documentation, neither will the AI agent. The more context you provide, the better the AI can interpret and analyze your data.

​

Curating the fields used by AI agents

You can use tags to categorize your metrics and dimensions in your YAML file to control which fields the AI uses. This helps focus the AI on the most relevant data for analysis.

Adding tags to metrics & dimensions

To configure which fields are used by your AI agent, you need to add tags to your metrics & dimensions in your YAML files. You can then use these tags when you create a new AI agent to filter the metrics & dimensions available for each AI agent.

- name: orders
  columns:
    - name: status
      meta:
        dimension:
          tags: ai #    <--------- tagging the dimension
     - name: location
      meta:
        dimension:
          tags: ['ai', 'operations'] #    <--------- adding many tags
    - name: amount
      description: Total amount of the order
      meta:
        metrics:
          total_order_amount:
            type: sum
            format: usd
            round: 2
            tags: ai #    <--------- tagging the metric

Configuring tags used by each agent

For each AI agent, you can configure which fields are used to answer questions using the tags you’ve defined in your YAML files.

You can add one or many tags to this list. Fields with any of the tags in the list will be considered by the AI agent in that Slack channel.

​

Providing custom instructions

You can provide custom instructions to each AI agent on its settings page. Watch the video to learn more.

​

Setting up multiple agents

Here’s a sneak peak at an alpha feature, multiple AI agents! You can set up a different agent for different tasks, different tones, languages, etc. and each one can have access to different datasets to focus results and give more accurate answers.

​

Connecting to Slack

Watch this video to learn how to setup an AI agent in Slack.