Tag
The article provides a walkthrough on setting and enforcing cost controls using LangSmith LLM Gateway to manage expenses when using multiple LLM agents.
LangChain has rebuilt Dashboards in LangSmith to improve investigation and reporting, featuring KPIs next to trends, metric comparison, breakdowns by model or user, notes, and freely arrangeable layouts.
monday.com's Director of Engineering Dor Cohen will speak at Interrupt London about building a dual-pipeline LLM eval system using LangSmith production traces for online and offline evaluation.
LangSmith's LLM Gateway now supports Kimi K3 and other open models via Gateway Credits, letting users call hosted models with just a LangSmith API key without configuring provider secrets.
LangChain announces that Spring Health's Sr. Director of Engineering Marissa Saunders will speak at Interrupt NYC, a conference on AI agents taking place September 24 in New York City.
LangSmith LLM Gateway is now in public beta, offering centralized governance for model calls in production agents — including spend caps, rate limits, model fallbacks, and per-customer policies to prevent outages and cost overruns.
Google Devs shares how to use Google ADK, Gemini Live, and LangSmith to build voice agents with full traceability of interactions, including tool calls and token costs.
Vinay Narayanamurthy, Principal Engineer at Home Depot, will speak at the LangSmith Roadshow in Atlanta on Aug 11 about building, testing, deploying, and monitoring agents in production.
This article explains how Similarweb evaluates long-form agent research reports using LangSmith, combining deterministic checks for tool calls and LLM-as-judge scoring for quality, with a focus on making regressions inspectable and enabling A/B comparisons.
CreditGenie uses LangSmith to debug thousands of agent traces and generate targeted test questions from production data.
A tutorial by Darsh on how to trace and monitor local AI agents using LangSmith, LangChain, Ollama, and Qwen, enabling inspection of model and tool calls, latency, and usage.
LangSmith officially launched Python-side voice tracing support, covering four mainstream frameworks: Pipecat, LiveKit, OpenAI Realtime, and Gemini Live. It brings voice conversations into the same observable, evaluable workflow as text agents, solving the pain point of poor debuggability in voice agents.
LangChain released a tracing plugin that converts every Cursor AI agent session into a structured trace in LangSmith, including model runs, tool calls, and nested subagent work, part of a series comparing coding-agent traces.
LangChain announces a summer AMA series on the agent development lifecycle using LangSmith, covering building, deploying, monitoring, improving, and governing agents.
LangChain introduces IssueBench, a detailed evaluation suite for Engine, a continual learning agent in LangSmith that automatically improves agents based on traces.
LangChain is hosting a LangSmith Roadshow, a half-day hands-on event covering LangSmith Engine and Managed Deep Agents with live demos, customer stories, and lab sessions.
Toyota's enterprise AI team shared the ToyotaGPT platform at the Interrupt conference. Based on LangGraph and LangSmith, it reduced AI agent delivery from 6 months to 4 days, and has over 50 agents running in production, saving millions of dollars.
LangChain is hosting a Summer AMA Series with practical walkthroughs and live Q&A about LangSmith.
LangChain released a tracing plugin for Codex sessions in LangSmith, enabling detailed traces of every turn including tool calls and token usage, configurable with just two blocks and a flag.
LangChain demonstrates an agent that drafts a cited VC investment memo in ~90 seconds for $0.40 using the Perplexity Agent API and LangGraph, with four parallel research nodes and a synthesizer.