> For the complete documentation index, see [llms.txt](https://docs.tonic.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.tonic.ai/app/structural-ai-and-agent/structural-ai-use/structural-ai-features.md).

# 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](/app/structural-ai-and-agent/structural-ai-use/structural-ai-data-flow-privacy.md).

For information about how to configure LLM connections and usage, go to [Structural Cloud LLM configuration](/app/structural-ai-and-agent/structural-ai-use/structural-cloud-llm-configuration.md) or [Self-hosted LLM configuration](/app/structural-ai-and-agent/structural-ai-use/self-hosted-llm-configuration.md).

## Structural Agent

The [Structural Agent](/app/structural-ai-and-agent/agent-about.md) 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](/app/generation/identify-sensitive-data/running-the-structural-sensitivity-scan.md#llm-based-sensitivity-detection-medium-confidence) uses the schema and, optionally, sample source data values to help to identify sensitive columns.

## LLM-based sensitivity rules

LLM-based [sensitivity rules](/app/generation/identify-sensitive-data/custom-sensitivity-rules.md) 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](/app/generation/generators/generator-reference/custom-categorical.md) 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](/app/generation/generators/generator-reference/text-composition.md) 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](/app/workspace/workspace-configuration-settings/data-connection-settings/connection-testing.md) 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

{% hint style="info" %}
**Required workspace permission:** Download job logs
{% endhint %}

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](/app/api/structural-mcp-server.md).


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.tonic.ai/app/structural-ai-and-agent/structural-ai-use/structural-ai-features.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.