AI analysis overview
Target Audience: Non technical users
TL;DR
Toucan.ai uses AI analysis to enrich connected databases with semantic metadata, which is required for accurate chart generation and security configuration.
When to use this
Use this page to understand how metadata affects the platform's AI reasoning and when to initiate the analysis process.
Purpose of AI Analysis
The Analyze feature adds a semantic layer to raw data. This process is a required step for the following workflows:
Natural Language Queries: Enriches tables and columns so the AI can interpret user prompts.
Dashboard Generation: Improves the selection of relevant charts based on data types.
Security Preparation: Prepares column structures for Row-Level Security (RLS) mapping by inferring data types, which determines the available comparison operators
User Clarity: Replaces raw database names with human-readable display names.
Core Functionality
When the Analyze feature is triggered, Toucan.ai performs the following automated actions on a selected schema:
Selection Phase
Before automated actions begin, the platform triggers a selection modal. This allows users to target specific subsets of data rather than analyzing the entire connection, optimizing processing time and relevance
Tables
Generates a description summarizing the table's content (e.g., "Provides regional sales data").
Columns
Infers a semantic field type: Category, Text, Date, or Metric.
Naming
Creates a display name for use in the UI.
Context
Generates a short explanation for what each specific column represents.
Note: All AI-generated metadata remains editable. Manual refinement is required for ambiguous columns to ensure visualization accuracy.
Refresh schema: If your database structure changes (e.g., added tables or modified columns), use the Refresh Schema button. This triggers a re-scan of your metadata, ensuring Toucan-AI reflects the most current architecture and maintains query accuracy.
Usage Requirements
Timing: Initiate analysis immediately after connecting a new database or whenever the underlying schema changes.
Prerequisite: Analysis must be completed before configuring RLS or creating AI-powered dashboards.
Persona: This feature is designed for Product Managers and Data Analysts preparing data for end-users.
Limitations
Sample-Based: Inference is based on schema structure and sampled values; it is not an exhaustive data audit.
Scope: Multiple schemas and tables can be selected for analysis within a single operation via the selection modal.
Manual Review: Toucan.ai assumes users will validate generated metadata before production use.
Last updated
Was this helpful?