Loomi Analytics Assistant

Loomi Analytics Assistant allows you to generate analysis (report, funnel, trend, segmentation) and definition (metrics, aggregate, running aggregates, and expressions) by asking questions or sending requests in human language. It also provides explanations for the definitions it generates.

Why Use Loomi Analytics Assistant

Loomi Assistant helps you quickly create any analysis and get insights from data without a steep learning curve and hours spent building it.

How Loomi Analytics Assistant Works

Getting Started with Loomi Analytics Assistant

1. Launch

Open Loomi Analytics Assistant by clicking on the Star icon in the top right corner.

2. Enter Request

Enter your request in the text field, or click to choose from a pre-defined prompt.

3. Send Request

Click on the Send button or press Enter to send a request.

4. Check the Results

Verify the results once your analysis or definition is complete to ensure data accuracy.

5. Let the Assistant explain

After creating the analysis, you can see a button "Explain this definition". If you click it, AI will explain the definition, not the results.

6. Provide Feedback

We welcome your feedback. We aim for perfection, and your insights are invaluable to us. Evaluate each response by clicking the Thumbs Up (positive) or Thumbs Down (negative) icon. Specify what was particularly good or what could be improved.

Use Case Examples

The Loomi Analytics Assistant always provides the best answers and responses possible.

• Build reports — "Show me email campaign evaluation with metrics - sent, delivered, opened, clicked, open rate, and click rate all in last 30 days drilled down by country"
• Build trends — "Show me the trend of session_start events in the last 7 days"
• Build metrics — "Create metric defining active users in the last 7 days"
• Build segmentation — "Create segmentation based on the number of purchases"
• Build aggregate — "Create aggregate defining total spend"
• Build expression — "Create an expression defining the time between purchase and the last clicked campaigns"

Limitations

• There is a length limit for each conversation. The limit is based on the number of characters. When the limit is hit, an error occurs.
• The Assistant can't make any adjustments to the definition, which was created manually.
• The Assistant can't refer to any existing definition or analysis.
• The Assistant can't build Event segmentation.
• The Assistant can't build Flows.
• The Assistant can't build Geo Analysis.
• The Assistant can't build Retention.

Data Protection and Privacy

The Loomi Assistant feature (also known as the Copilot) prioritizes data privacy and security. It does not collect, process, or store any Personally Identifiable Information (PII). Instead, the system interacts solely with anonymized data related to the data schema, including customer attributes, event types, and event attributes, without tracking any values for these attributes.

Data Privacy

• No PII Handling: The Assistant feature does not handle any PII.
• Data schema only: The Assistant operates solely with the project’s data schema. It does not access any stored data or examples of tracked values.

Prompting

• No saved prompts: The Assistant does not store any prompts written by users. It only uses the prompts to maintain the context of the conversation. Prompts are discarded when users start a new conversation or manually clear the context.
• No background processes: The Assistant does not work autonomously. Users trigger every interaction. This means that if a user does not send any requests to the Assistant, no actions are taken in the background.
• Improvements: We store prompts only for internal purposes, specifically when users provide feedback on a particular conversation. This storage helps us understand the context of the feedback.

Compliance

• GDPR Compliant: The Copilot feature is being reviewed within the privacy-by-design process and fully complies with the General Data Protection Regulation (GDPR) and other applicable data protection regulations.
• Regular Audits: We conduct regular tests and development to ensure continuous compliance with regulations.

Transparency

• Comprehensive Documentation: This documentation offers detailed insights into our data handling practices.
• User Communication: Users are notified in advance of any significant changes to the feature, especially those that affect data privacy and security. Consent is always required from users before they can use the feature.
• Feedback Mechanism: Users can raise concerns or provide feedback through our dedicated communication support channels.