Data flow and privacy in Structural AI

Overall interaction flows with an LLM

The following diagrams show the general interaction between Structural and an LLM based on the Structural deployment.

Structural Cloud

On Structural Cloud, all users use the same LLM, which is managed by Tonic.ai.

Structural Cloud interaction with the LLM

Self-hosted instances that use the hosted LLM

Self-hosted instances can choose to use the LLM that Tonic.ai maintains.

For each customer, requests to the LLM are routed through a SaaS proxy to the hosted LLM in the appropriate region.

Self-hosted Structural interaction with the hosted LLM

Self-hosted instances that use their own LLM connection

Self-hosted instances can also establish their own connection to an LLM.

Self-hosted Structural interaction with a custom LLM connection

Flows for AI features

The following flows show the request and results for specific Structural AI features.

LLM-based sensitivity detection

Here is a high-level flow of LLM-based sensitivity detection.

High-level flow for LLM-based sensitivity detection

To complete the analysis, Structural sends the following to the LLM to complete the analysis:

• Database schema.
• By default, sample source data values.
• LLM-based sensitivity rules

To manage LLM-based sensitivity detection:

• You can exclude the sample data, and only send the schema information.
• You can disable it entirely.

For more information go to the information on configuring AI-based functionality for Structural Cloud and on self-hosted instances.

Structural Agent conversations

Here is a high-level overview of a Structural Agent interaction:

High-level flow for Structural Agent interactions

When it sends your prompts to the LLM, to provide context for tasks such as recommending generators, Structural also sends:

• The database schema.
• By default, representative data samples.

You can configure Structural to never send any sample data to the LLM. This configuration would also prevent data from being sent as part of the LLM-based sensitivity detection.

For more information go to the information on configuring AI-based functionality for Structural Cloud and on self-hosted instances.

Generator configuration

The Custom Categorical and Text Composition generators both include a prompt field to use to configure the generator.

Structural sends the prompt to the LLM. The LLM returns the list of values or the template.

Flow for LLM-assisted generator configuration

Data connection troubleshooting

When a data connection test fails, Structural provides an option to use the LLM to troubleshoot the issue.

Structural sends to the LLM the connection details and the error. The LLM analyzes the information and returns suggestions for how to resolve the connection issue.

Flow for LLM-assisted data connection troubleshooting

How Structural stores Agent conversations

Structural stores your Structural Agent conversations on your computer, in your local browser storage.

How the LLM uses information

On Structural Cloud and on our hosted LLM, our usage of information specifically follows the usage policy for Anthropic on Amazon Bedrock.

For all LLM-based interactions, input prompts and generated responses are only used for workspace data analysis and configuration.

Prompts and responses are never used to train the underlying models.

However, as a best practice, we recommend that you do not include highly sensitive values in your manual prompts.