Getting started with AI agents

Learn how to create and configure your first AI agent in Lightdash

Getting started with AI agents is simple - you can begin using them right away on any project in your Lightdash instance.

1. Create your first agent

   Set up a new AI agent in your Lightdash project, follow the guide

2. Configure your agent

   Use tags to control which data the agent can access, follow the guide.

3. Connect to Slack

   Enable team collaboration through Slack, follow the guide

Creating your first AI agent

Go to Ask AI

This will be your entry point to working with the AI agent

Create a new agent

Go to the agent dropdown and click Create new agent at the bottom

Configure your agent

Name and image

Give your agent a memorable name and visual identity

Instructions

Provide context to guide your agent’s reasoning and ensure responses match your expectations. Your instructions can include any of the following components. Each one helps the agent understand your data, your business, and how you want insights delivered:

• Domain knowledge - Describe the industry or subject area the AI should think within. Include relevant terminology, methodologies, frameworks, and technical concepts.

• Company context - Explain the business background behind your analysis. Add details about your goals, product, target audience, strategy, or any constraints that influence how insights should be generated.

• Analysis preferences - Clarify how you want the AI to approach analysis. Specify preferred metrics, dimensions, chart types, visualization styles, and reporting formats so results match your expectations.

• Role & expertise - Tell the AI what role it should adopt (e.g., “Senior Marketing Analyst”). Include the communication style, depth of explanation, and level of decision-making authority you expect.

The more context you provide, the more accurate, relevant, and predictable your agent’s responses will be.

Enable Data Access (optional)

Enable data access to allow your agent to analyze actual query results and provide insights based on the data. When disabled, agents work with metadata only. Learn how to enable data access

User and Group Access (optional)

Control which users and groups can access your agent through the agent settings. For detailed guidance on how to configure data access control, see here

Tags (optional)

Use tags in the Lightdash metadata to control which metrics and dimensions the agent can access. Tags help you restrict your agent to a specific slice of your semantic layer.

1. Tag your dbt model dimensions and metrics with the tags you want - your agent will only have access to those dimensions or metrics that have matching tags.

View code examples

dbt 1.10+

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

2. Add the corresponding tags to your agent settings under the Tags field. This tells the agent which tagged dimensions and metrics it should access.

3. For more technical users who want to configure tagging rules in more detail - including how tags interact with permissions and schema visibility - see the Data access control section.

Enable Self-Improvement (optional, Beta)

Allow your agent to propose changes to your semantic layer, including updating descriptions and creating new metrics. Changes are tracked in changesets for review. Read more on self-improvement (beta) feature.

Slack Integration

Connect your agent to Slack channels so users can interact directly from Slack. Check out all the cool ways to integrate your agent into slack here

1. Add Slack to your organization in organization settings. An admin needs to complete this step. See the how-to guide.
2. Add the desired slack channel to your agent integration settings.

3. Add the Lightdash for analytics app to your desired slack channel by going to #channel —> Edit settings —> Integrations:

4. Now you can interact with your AI agent in slack just as you would in the Lightdash UI. Start asking questions like “What kind of data can you access?” or “Show me total order amount over time”.

5. You can also summon the bot on a thread to continue the conversation. In order for the bot to be able to respond, you need to enable this context sharing in your Lightdash Integrations settings.

Once you’re set up - whether in the UI or in Slack - you can start asking questions immediately! Try asking “What kind of data can you access?” to get started:

Setting up multiple agents

You can create multiple AI agents, each configured for different tasks, tones, languages, or teams. Each agent can have access to different datasets to focus results and give more accurate answers. Multiple AI agents can be used in the same Slack channel. Based on your question, the best agent to respond will be chosen - if it’s unclear, you’ll be prompted to choose which agent you’d like to answer.