SW1 for Observability Self-Hosted FAQ

This topic provides frequently asked questions for SW1 in Observability Self-Hosted environments.

Dated July 2026

This page may be updated from time to time, so check back regularly for the latest version of these FAQs.

What is SW1?

SW1 is the SolarWinds AI agent built into supported SolarWinds products. It lets users ask natural-language questions inside the product and receive brief explanations, insights, and recommended next steps based on the data they already have access to. Please note that SW1 functionality is evolving rapidly. For the latest features and improvements available in your product, refer to the product documentation pages.

How do you set it up?

Setup depends on the product and deployment model. For self-hosted deployments, SW1 is enabled by configuring Platform Connect. The Platform Connect feature is opt-in by admins only.

What data is being sent?

Only a subset of data relevant to the request is currently sent to SW1. SW1 uses data the product already collects, and only data the user is already allowed to access is available as input for that user in SW1. If you choose to store sensitive data in the product and then ask SW1 a question that requires that context, a limited amount of that data may be included in the request so SW1 can return a more accurate response.

How is that data being sent?

The relevant data is currently encrypted in transit. For self-hosted deployments, relevant request data is sent through Platform Connect to the SolarWinds platform, where the request is processed through the agentic and LLM gateway layers before a response is returned to the product UI.

For self-hosted deployments, the high-level request path is shown in the figure below.

How long is my data stored?

SW1 prompts, outputs, and related logs are retained according to SolarWinds privacy and retention policies. See https://www.solarwinds.com/legal/privacy for more information on those policies.

What controls are in place to ensure my data privacy?

SolarWinds takes the same Secure by Design principles outlined in our Information Security policies into account for SW1.

• All in-product activities remain governed by existing role-based access controls.
• Data exchanged with external model providers is encrypted in transit.
• Customers can disable the AI Agent at the product or tenant level where available.

For additional information, see the SolarWinds Privacy Notice and SolarWinds Information Security pages.

Is my data used to train AI models?

No. Customer data is not used to train the underlying AI models for the benefit of large language model providers, and interactions with model providers are designed to be stateless at the LLM layer.

SW1 uses commercially available foundation models accessed through managed provider APIs and secure interaction patterns.

Does SW1 change anything in my environment without my consent?

No. For SolarWinds products that offer SW1, SolarWinds currently follows a human-in-the-loop approach and requires user consent before any change to your environment is made. SW1 can only act within the permissions the user already has access to.