LangChain Rebuilds LangSmith Trace Filtering for Faster Agent Observability
LangChain · x · 2026-09-18
LangChain announced a ground-up rebuild of the filtering experience in LangSmith, its agent observability platform. The update makes it easier to build precise queries to narrow down runs, find the exact runs you need, and understand why a result matched.
Contributor arjunnatarajan noted that agent observability is meaningless if you can't quickly find the traces you're looking for, which motivated the rework.
Related event: LangSmith Rebuilds Agent Trace Filtering(2 posts)→
More from coding & agent
- Notion launches Skills API: edit team skills once, use them in ChatGPT, Claude and agents — thesaraharminta · 2026-09-18
- Why you should build your custom agent harness with MCP tools — omarsar0 · 2026-09-18
- Alignment drift study: one reward hack raises GPT-5.5's re-hack rate from 10% to 64% — maksym_andr · 2026-09-18
- Typesafe goes from two-year stealth cold start to 140k waitlist signups in under 36 hours — damianplayer · 2026-09-18
- New blog finds data issues in a frontier benchmark, ports Agents' Last Exam CLI subset to Verifiers v1 — dejavucoder · 2026-09-18
- After pushing 2B tokens through DeepSeek V4.1 Flash, dev cuts AI bill from $300 to $30/month — gaganghotra_ · 2026-09-18