# The Compliance API now returns the text each organization member saved as Instructions for Claude in… By Steven Van · 2026-10-15 Claude Enterprise admins can read members' saved Instructions for Claude and Cowork Global instructions through a beta Compliance API endpoint. The [Anthropic]() Compliance API now returns the text each organization member saved as Instructions for Claude in claude.ai and as Global instructions in Cowork. The feature is in beta for Claude Enterprise organizations, and it was listed in the [Compliance API]() release notes for October 15, 2026. ## How to call it The new endpoint is GET /v1/compliance/organizations/{org\_uuid}/user\_preferences. It works with an existing Compliance Access Key that carries the read:compliance\_user\_data scope. The vendor's docs list the call as "List user preferences". ## Who can use it The endpoint is in beta and available to **Claude Enterprise** organizations. Compliance Access Keys are created in claude.ai. Admin API keys, which are created in Claude Console, reach only the Activity Feed. Like the other /v1/compliance/\* endpoints, requests authenticate through the x-api-key header and take the anthropic-version header. They share a limit of 600 requests per minute per parent organization. ![Anthropic]() Anthropic Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems. [View Anthropic →]() [Original source]() [Read The Compliance API now returns the text each organization member saved as Instructions for Claude in… on Creators Toolbox]() --- Canonical source: https://creatorstoolbox.com/blog/anthropic-the-compliance-api-now-returns-the-text-each-organization-member