Skip to content
Alation Agent Studio Documentation

Chart Generation

The chart generation agent creates custom data visualizations based on user requests.

How it works

Section titled “How it works”

The agent uses this workflow:

  1. Receives a natural language request from the user
  2. Executes queries to obtain relevant data for the visualization
  3. Generates the requested chart(s)

Input parameters

Section titled “Input parameters”

Required:

  • message (string): The natural language question or request to send to the agent
  • data_product_id (string): The data product to query

Optional:

  • data_product_version (string): The data product version to query. Defaults to the active version when omitted.

Output format

Section titled “Output format”

The agent produces a series of thinking, tool call, tool return, and text blocks as it works through the user request. The final message, assuming no errors, is a string. The chart(s) generated are available as html and json vega configs with successful charting tool return blocks.

Available tools

Section titled “Available tools”

The agent is configured with 3 tools:

Get data schema

Section titled “Get data schema”

Retrieves the schema for tables in the data product. Optionally supports semantic search of sample values.

Key parameters:

  • data_product_id: The data product to get schema for
  • query: Optional semantic search query for sample values

SQL execution

Section titled “SQL execution”

Executes SQL queries against the data product’s database. The tool automatically handles result serialization and may limit rows/columns for very large results.

Key parameters:

  • data_product_id: The data product to query
  • sql: The SQL query to execute
  • result_table_name: A semantic name for the result table

Chart generation from asset

Section titled “Chart generation from asset”

Generates visualizations from an asset (a CSV produced by a prior SQL execution). The agent uses ChartGrammar — a structured chart configuration — by default; if the requested chart can’t be expressed in ChartGrammar, the agent falls back to providing custom Altair Python code via chart_code_snippet.

Key parameters:

  • asset_id (required): ID of the CSV asset containing the data
  • chart_grammar: Structured chart configuration (preferred path)
  • chart_code_snippet: Python function using Altair (fallback when ChartGrammar can’t express the chart; required with image_title)
  • image_title: Title for the chart (required with chart_code_snippet)

Behavior notes

Section titled “Behavior notes”
  • The agent always uses result tables from executed queries to answer questions (never synthesizes data)
  • For complex questions, the agent may execute multiple queries to explore the dataset or obtain intermediate results
  • When generating charts, it returns the first reasonable visualization without excessive iteration
  • Charts are generated using Altair and returned as JSON representations
Section titled “Related”