LangSmith Launches LLM Gateway to Redact PII in AI Requests

LangChain · x · 2026-08-10

LangChain announced new Data Protection Controls for its LangSmith LLM Gateway, now in public beta for Enterprise users.

The feature automatically detects, redacts, and replaces PII and secrets (like API keys) in requests before they reach model providers. It restores original values in the model provider's response, ensuring redaction doesn't impact agent functionality. Sensitive data is also redacted from the traces recorded in LangSmith.

Original post →

More from coding & agent

coding & agent channel →