Skip to main content

Discover answers and insights from the Anthropic team

Search results for:detection
CSAM Detection and Reporting
If you receive a notification from us about CSAM detection and believe we’ve made an error, please email
Our Approach to User Safety
Here are some of the safety features we’ve introduced: Detection models that flag potentially harmful… Safety filters on prompts, which may block responses from the model when our detection models flag content… Enhanced safety filters, which allow us to increase the sensitivity of our detection models
“Try fixing with Claude” for Artifact errors
"Try fixing with Claude" is designed to help you quickly address any errors that are detected when generating
I would like to input sensitive data into free Claude.ai, or my Pro/Max account. Who can view my conversations?
for trust and safety review, we may use or analyze those conversations to improve our ability to detect
Setting up Single Sign-On on the Enterprise plan
Enabling advanced group mappings before the groups have been detected is not recommended as it could… Logout and log back in to allow our systems to detect new groups… Click the “sync now” button next to the “Directory sync (SCIM)” section to allow our system to detect
Using the Gmail and Google Calendar Integrations
Claude will automatically detect that it needs to access these data sources and use the appropriate tool
Law Enforcement Requests
Name of Court/Policy Department/Authority/Agency Name of Contact Person Handling this Matter (Detective
API Key Best Practices: Keeping Your Keys Safe and Secure
If an Anthropic API key is detected in a public GitHub repository, GitHub immediately notifies Anthropic
API Safeguards Tools
Enable additional safety filters - free real-time moderation tooling built by Anthropic for helping detect