For the complete documentation index, see llms.txt. This page is also available as Markdown.

Structural AI features

Tonic Structural currently offers the following AI features.

For information about the associated flows for these features, go to Data flow and privacy in Structural AI.

For information about how to configure LLM connections and usage, go to Structural Cloud LLM configuration or Self-hosted LLM configuration.

Structural Agent

The Structural Agent is a chat-based AI assistant that helps you to configure your workspace for data generation.

LLM-based sensitivity detection

During sensitivity detection, the LLM-based detection process uses the schema and, optionally, sample source data values to help to identify sensitive columns.

LLM-based sensitivity rules

LLM-based sensitivity rules use the sensitivity rule description to identify matching columns.

They are processed during LLM-based sensitivity detection.

Custom Categorical value creation

For the Custom Categorical generator, you can provide a prompt for the LLM to use to create the available values.

For example, 1,000 common pharmaceuticals.

Text Composition template creation

For the Text Composition generator, you can provide a prompt for the LLM to use to create the template.

For example, Use the first character of the FIRST_NAME column, followed by a period and the value of the LAST_NAME column, followed by email.com, all lowercase.

Data connection test failure troubleshooting

When a data connection test fails, Structural displays an Ask AI prompt that sends a request to an LLM to troubleshoot the issue and suggest next steps.

Job failure troubleshooting

Required workspace permission: Download job logs

For the the following types of jobs:

  • Sensitivity scans

  • Data generation jobs

  • Upsert jobs

  • Collection scans

The job details include Ask AI prompt that sends a request to an LLM to troubleshoot the issue and suggest next steps.

Structural MCP server

The Structural MCP server allows you to use AI clients such as Claude Code to interact with Structural using the same natural language prompts that you provide in the Structural Agent.

For information on how to set up access to the MCP server, go to Using the Structural MCP server.

Last updated

Was this helpful?