LangSmith adds trace access controls so engineers debug agents without exposing sensitive data
LangChain · x · 2026-11-18
LangChain shipped three new trace access controls in LangSmith Enterprise plans:
- Input/output visibility control: engineers can debug with run trees, latency and cost stats, without seeing sensitive raw inputs and outputs;
- User groups: manage data access and workspace membership team-by-team;
- Trace-level policies: use root run metadata to decide who can view specific traces.
LangChain notes production traces often contain names, health data, or payment details, and these controls aim to reconcile least-privilege compliance with engineers' debugging needs.
Related event: LangSmith adds three trace data access controls(2 posts)→
More from coding & agent
- Agent memory benchmarks measure recall, but provenance is what bites in production — Mr_Daud_9899 · 2026-11-18
- Replit launches Missions, an agent-swarm harness that hits your goals within a set budget — amasad · 2026-11-18
- YC Paper Club: why the harness matters more than the model — eherrerosj · 2026-11-18
- AI-built Paris replica streams city blocks in real time with historically accurate traffic — Dimillian · 2026-11-18
- Reflection launches Trusted Access Program, starting with autonomous pentest tool Laser — brandondamos · 2026-11-18
- Tiny 2.6B local model runs an AI town, with every decision captured via Otel in Agent Lens — coreweavedevs · 2026-11-18