Click any tag below to further narrow down your results
Links
This article details which Anthropic commercial products and API features qualify under a HIPAA Business Associate Agreement. It breaks down covered and non-covered services, notes beta and third-party integration exclusions, and highlights ZDR requirements for handling PHI in Claude Code.
- Core Claude for Work features (chat history, Artifacts, voice, web search, research, file creation/code execution without external network access) are BAA-covered, but third-party integrations like MCPs/Connectors, Enterprise Search, and Claude in Chrome are not once data leaves Anthropic.
- On the API side, Messages API and related tools (prompt caching, structured outputs, memory, web search, Bash/text-editor) plus Token Counting, Models, Org Management, and Compliance APIs are covered, while Batch API, Files API, Skills API, Code Execution, Computer Use, and Web Fetch are excluded.
- For Claude Code, only the CLI with Zero-Data-Retention enabled qualifies for BAA coverage—the web, desktop, review, and security betas don't support ZDR and fall outside it.
- Beta features like Cowork and Claude for Office are entirely excluded from BAA coverage, requiring separate data-handling safeguards for any PHI use.
Many users are unaware that conversations with consumer AI about health issues lack legal protections, unlike communications with licensed healthcare providers. This article highlights the risks of disclosing personal health information to AI, which can be subpoenaed in legal situations, exposing users to potential misuse of their private data. It emphasizes the importance of understanding what privileges are lost when opting for AI assistance over traditional healthcare communications.
- Conversations with AI like ChatGPT or Claude aren't protected by legal privilege, unlike those with doctors or therapists, meaning they can be subpoenaed and used in court
- A wrongful death lawsuit already involved private mental health conversations being submitted as evidence
- OpenAI admits it doesn't train on user chats but authorized staff can still access them, leaving data vulnerable to legal requests
- Surveys show many users mistakenly believe AI chats carry the same confidentiality as conversations with doctors or lawyers
+ chatgpt
claude
+ health data privacy
+ legal privilege
+ subpoena risk
healthcare
+ confidentiality