SmithDB converts each ingested trace into a single standard message format and builds a trajectory view across them. 💡 ICYMI: A trajectory is a readable view of an agent session. Learn more at https://
langchain.com/blog/langsmith
-trajectories-tracing
…
@langchain
-
SmithDB Builds Standardized Trajectories Across Agent Trace Messages
By
–
-
LangSmith AI Search Streams Model Checked Trajectory Matches
By
–
🧵 Behind the scenes of AI Search in LangSmith:
— LangChain (@LangChain) 16 octobre 2026
TL;DR
1️⃣ SmithDB turns traces into readable trajectories. Structured filters narrow the candidates when you search
2️⃣ A model checks each remaining trajectory against your description and streams back matches pic.twitter.com/YWBjhFkeQ6🧵 Behind the scenes of AI Search in LangSmith: TL;DR 1️⃣ SmithDB turns traces into readable trajectories. Structured filters narrow the candidates when you search 2️⃣ A model checks each remaining trajectory against your description and streams back matches
-
LangSmith Analysis Finds Small Relevant Slices in Large Agent Trajectories
By
–
AI Search reads each trajectory within a fixed token budget. Most questions about behavior only need a small slice, and we checked that on 150 conversations from Open SWE, the coding agent our team uses every day. ✅ The median ran 84K tokens
✅ About 1.5K of that was the -
AI Search Combines Structured Filtering With Parallel Trajectory Checks
By
–
When you search, structured filters like a time range narrow the candidates first. Then a small, fast model checks each remaining trajectory against your description, with many checks running in parallel. Each one usually takes under half second. Matches stream back as they’re
-
Guide Covers Architectures and Evaluation for Healthcare Agents in Production
By
–
What does it take to move healthcare and life sciences agents from experimentation into trusted production systems? Explore the architectures, evaluation practices, and production patterns teams are using as agents take on more complex work: ➡️ https://
info.langchain.com/guide/scaling-
agents-in-healthcare-and-life-sciences
… -
Opine Gates Prompt and Model Changes With LangSmith Evaluations
By
–
LangSmith for Startups spotlight: @tryopine
— LangChain (@LangChain) 15 octobre 2026
The customer intelligence layer for revenue teams
Opine traces every production LLM run through LangSmith, and gates every prompt and model change behind LangSmith evals.
See what Opine looks like on your hardest open deal at… pic.twitter.com/WtPnMfx9nnLangSmith for Startups spotlight: @tryopine The customer intelligence layer for revenue teams Opine traces every production LLM run through LangSmith, and gates every prompt and model change behind LangSmith evals. See what Opine looks like on your hardest open deal at
-
Educational Resource Answers Common Questions About Agent Evaluations
By
–
Our education team answered the most common questions we've received over the years about agent evals. Check it out ⤵️
-
LangSmith Helps Teams Find Traces and Align AI Evaluators
By
–
"I can finally find the data that I want without having to fight my tooling."
— LangChain (@LangChain) 15 octobre 2026
LangSmith helps @TrustVanta find traces fast, align evaluators to labeled examples, and improve AI quality end to end.
⏯️ Zheng Tao on why "LangSmith gets it." pic.twitter.com/iBqIKLkFtS"I can finally find the data that I want without having to fight my tooling." LangSmith helps @TrustVanta find traces fast, align evaluators to labeled examples, and improve AI quality end to end. ⏯️ Zheng Tao on why "LangSmith gets it."
-
Nemotron Super VL Achieves High Pass Rates in Deep Agents Tests
By
–
Nemotron 3.5 Super VL from @NVIDIAAI brings vision, reasoning & tool use to Deep Agents via ChatNVIDIA. Open weights. 120B parameters, 12B active. Nemotron 3.5 Super VL averaged an 87% pass rate on our Deep Agents behavioral suite. Speed stood out, too. On our Harbor-lite
-
Deep Agents Harness Moves Context Outside the Active Window
By
–
How do agents remember? The longer an agent runs, the more it takes in (instructions, tool results, files, and drafts), which results in decreased accuracy and reasoning. Read how LangChain's Deep Agents harness addresses this by moving context out of the active window without