Adobe LLM Optimizer: Data Retention and Privacy Compliance for Webpage Content
This article addresses questions regarding data retention and privacy compliance when using Adobe LLM Optimizer to scan webpage content.
Description description
Environment
Adobe Experience Manager (all versions) with Adobe LLM Optimizer
Issue/Symptoms
A data privacy team requested clarification on how Adobe LLM Optimizer handles data retention and privacy when scanning webpages or URLs. The specific queries include:
- Does Adobe LLM Optimizer read and store the content of scanned webpages?
- If content is stored, is it deleted after insights are generated, or is it retained on vendor servers?
- If retained, what is the retention duration and is there a defined deletion timeline?
No error messages or stack traces are associated with this inquiry.
Resolution resolution
Follow these steps to resolve the issue:
-
Review the official Adobe documentation on LLM Optimizer data retention and privacy compliance:
-
Note the following key points:
-
Adobe LLM Optimizer doesn’t retain personally identifiable information (PII) or private content. It may retain public content and other analyzed product data that it stores for insights and trend reporting, and that stored data may remain until the customer opts out of the product. Raw source data such as CDN logs isn’t retained as raw logs after processing; only derived or aggregated product data is kept.
-
User identity (name and email address) is managed through Adobe IMS (Identity Management System) and isn’t stored as product data within LLM Optimizer.
-
User retention and access are managed via the Adobe Admin Console, consistent with other Adobe Experience Manager products. For more information, refer to:
-
Cause
Adobe LLM Optimizer is designed to avoid retention of PII or private webpage content, and user data management is handled through the Adobe identity and access management infrastructure.