Interface overview
This page has three main areas:
Sidebar
- Chat - The current active section (highlighted with pencil icon) where you can edit your data layer
- Sources - View raw data connections
- MCP - Connect to external tools via Model Context Protocol
- Conversations - See your past questions and AstroBee’s responses
Center panel
The center panel helps you explore your data layer through three tabs:- Tables
- Description
- Data Map
View all entities in your data layer. Click any entity to see its details in the entity browser. The right side shows Business Value (what insights this data layer enables) and Model Details (version, database, patterns persisted, unmapped fields).
Entity browser
Click any entity in the Tables list to open its details. The entity browser has four tabs:- Data
- Description
- Properties & Relationships
- SQL
Preview actual data records from the selected entity. Shows sample values and data types with a 200-row preview. You can download the full data as CSV.
Understanding your data layer
Your data layer is a map of how your business concepts connect to your raw data and to each other. Here’s what makes it up:Entities
Each entity represents a core business concept that AstroBee has identified from your data:| Entity | Description |
|---|---|
| Company | Organization associated to contacts, product users, and billing based on website/domain |
| Contact | A person engaged via marketing/sales (lead, MQL, SQL, customer) from CRM |
| Product User | An application user with account activity and engagement metrics |
| Billing Account | The paying account profile used for invoicing and payments |
| Subscription | A recurring billing plan agreement status with MRR, currency, and start dates |
| Plan | The commercial tier (e.g., Starter, Growth, Enterprise) associated with users and subscriptions |
Properties
Properties describe each entity and come in different types:| Property Type | Description |
|---|---|
| Identifiers | Unique keys that identify each instance (e.g., customer_id, email) |
| Descriptive fields | Attributes and values (e.g., name, total_spend, created_date) |
| Calculated metrics | Derived values like averages or totals |
| Data types | String, Integer, Timestamp, etc. |
Relationships
Relationships show how entities connect to each other:| Relationship Type | Description |
|---|---|
| One to Many | One company has many billing accounts |
| Many to Many | Multiple relationships between entities |
Editing your data layer
To edit your data layer, type your requests in natural language in the chat input. AstroBee handles both simple and complex edits automatically. Simple changes like renaming a property complete in seconds, while complex changes like creating new entities with multi-table joins take longer as AstroBee reasons through the requirements.
Simple edits
Simple edits are fast, focused changes to individual properties or relationships. These complete quickly without requiring deep analysis.Making requests
Describe what you want to change in plain English:- “Rename Total Shipments to Shipments”
- “Add customer satisfaction metrics”
- “Normalize email addresses to lowercase for better matching”
- “Fix the join between Contacts and Users - emails don’t match”
Reviewing changes
After processing, you’ll see a Proposed Changes panel showing what will be modified. Click into an edited entity to see detailed changes with properties marked as Added, Modified, or Removed:
Saving your changes
Click Accept Changes to save. You’ll be prompted to enter a commit message describing your changes. After saving, you’ll see a success notification and the new version appears in your version history:
Complex edits
Complex edits involve creating new business entities, restructuring relationships, or synthesizing data across multiple sources. These take longer as AstroBee researches your data and reasons through the requirements. For example, you might request:- Complex entity creation - AstroBee creates new entities that consolidate data across multiple business domains
- Multi-table aggregation - Generates key measures like contact counts, user engagement metrics, billing account counts, and MRR calculations
- Intelligent relationships - Establishes proper connections between the new entity and existing entities
- SQL view generation - Creates sophisticated SQL that aggregates data from multiple systems
- Business logic integration - Applies normalization rules and assumptions for data consistency
Rename data layer
You can rename your entire data layer to better reflect your business or project. Click the ellipsis () next to your data layer name, select ” Rename” and enter a new name. The change applies immediately and creates a new version, updating both the display name and system identifier to keep your data layers organized as projects evolve.Delete data layer
To permanently delete a data layer, click the ellipsis () next to the data layer name and select ” Delete.” You’ll see a confirmation dialog warning that this action cannot be undone. Once deleted, the data layer is completely removed and you’ll be redirected to the model selection screen to choose or create a different data layer.Version management
Your data layer is versioned automatically:- Timestamps show when each version was created
- Version numbers increment with each change (v1, v2, v3, etc.)
- Commit messages describe what changed in each version
- Rollback capability lets you return to previous versions if needed
