| {"messages": [{"role": "system", "content": "You are a helpful assistant with knowledge about general topics."}, {"role": "user", "content": "What information do you have about Data usage - Anthropic?"}, {"role": "assistant", "content": "Anthropic home page English Search... Search... Navigation Resources Data usage Welcome Developer Guide API Guide Claude Code Model Context Protocol (MCP) Resources Release Notes Documentation Developer Discord Support Getting started Overview Set up Quickstart Memory management Common workflows Build with Claude Add Claude Code to your IDE Model Context Protocol (MCP) GitHub Actions Claude Code SDK Troubleshooting Deployment Overview Amazon Bedrock Google Vertex AI Corporate proxy LLM gateway Development containers Administration Identity and Access Management Security Monitoring Costs Reference CLI reference Interactive mode Slash commands Settings Resources Data usage Legal and compliance Data policies Data training policy By default, Anthropic does not train generative models using code or prompts that are sent to Claude Code. We aim to be fully transparent about how we use your data. We may use feedback to improve our products and services, but we will not train generative models using your feedback from Claude Code. Development Partner Program If you explicitly opt in to methods to provide us with materials to train on, such as via the Development Partner Program , we may use those materials provided to train our models. An organization admin can expressly opt-in to the Development Partner Program for their organization. Note that this program is available only for Anthropic first-party API, and not for Bedrock or Vertex users. Feedback transcripts If you choose to send us feedback about Claude Code, such as transcripts of your usage, Anthropic may use that feedback to debug related issues and improve Claude Codes functionality (e.g., to reduce the risk of similar bugs occurring in the future). We will not train generative models using this feedback. Given their potentially sensitive nature, we store user feedback transcripts for only 30 days. Data retention You can use an API key from a zero data retention organization. When doing so, Claude Code will not retain your chat transcripts on our servers. Users local Claude Code clients may store sessions locally for up to 30 days so that users can resume them. This behavior is configurable. Privacy safeguards We have implemented several safeguards to protect your data, including: Limited retention periods for sensitive information Restricted access to user session data Clear policies against using feedback for model training For full details, please review our Commercial Terms of Service and Privacy Policy . Data flow and dependencies Claude Code is installed from NPM . Claude Code runs locally. In order to interact with the LLM, Claude Code sends data over the network. This data includes all user prompts and model outputs. The data is encrypted in transit via TLS and is not encrypted at rest. Claude Code is compatible with most popular VPNs and LLM proxies. Claude Code is built on Anthropics APIs. For details regarding our APIs security controls, including our API logging procedures, please refer to compliance artifacts offered in the Anthropic Trust Center . Telemetry services Claude Code connects from users machines to the Statsig service to log operational metrics such as latency, reliability, and usage patterns. This logging does not include any code or file paths. Data is encrypted in transit using TLS and at rest using 256-bit AES encryption. Read more in the Statsig security documentation . To opt out of Statsig telemetry, set the DISABLE_TELEMETRY environment variable. Claude Code connects from users machines to Sentry for operational error logging. The data is encrypted in transit using TLS and at rest using 256-bit AES encryption. Read more in the Sentry security documentation . To opt out of error logging, set the DISABLE_ERROR_REPORTING environment variable. When users run the /bug command, a copy of their full conversation history including code is sent to Anthropic. The data is encrypted in transit and at rest. Optionally, a Github issue is created in "}]} | |