Tagged

LangChain News

Agents, middleware, evaluation and releases across the LangChain stack. Curated and summarized from dozens of sources by AIBriefs.

AnalysisDevelopers1 source

LangSmith traces cut MadrigalPharma agent production from 12 to 2 weeks

How-ToAI Agents1 source

How LangChain built an autonomous SRE agent for Kubernetes

The agent automates Kubernetes deployments through Deep Agents, gates every change behind human approval, and uses LangSmith tracing plus eval suites to verify performance.

LaunchAI Agents1 source

LangChain introduces Skills for agent task specialization

EventDevelopers1 source

Spring Health joins LangChain at Interrupt NYC

How-ToDevelopers1 source

Agent governance guide from LangChain covers cost, data, policy controls

How-ToDevelopers2 sources

How to Evaluate Voice Agents with LangSmith

The framework scores voice agents on three dimensions: execution (did the agent follow instructions), outcome (did the call achieve its goal), and experience (was the conversation smooth for the caller). LangSmith evaluation combines traces, code evaluators, LLM judges, and human review.

AnalysisAI Agents1 source

CX Agents in Production: Lessons from Lyft, Vodafone, LATAM Airlines

LangChain's blog post distills lessons learned from running customer experience agents in production at Lyft, Vodafone, and LATAM Airlines, covering real-world deployment patterns for CX agent systems.

LaunchDevelopers1 source

OpenWiki's code init prompt gets a major upgrade

LaunchDevelopers1 source

LangSmith LLM Gateway adds model fallbacks

LaunchDevelopers1 source

Deep Agents, LangGraph, LangChain add resilience features

How-ToCybersecurity1 source

Tutorial builds AI skill security auditing pipeline with NVIDIA SkillSpector

Walks through scanning AI skills with NVIDIA SkillSpector's LangGraph inspection pipeline, using a synthetic marketplace of clean, risky, malicious, and MCP-based skills, plus YARA rules, SARIF output, and CI policy gates.

EventDevelopers1 source

LangGraph Studio demo teases unnamed capability, tutorial floated

LaunchDevelopers1 source

LangChain's managed deepagents is moving to public beta

AnalysisDevelopers1 source

Stripe built Kai internal AI agent platform using LangGraph

Stripe's Knowledge AI Platform, or Kai, reached 5,000 internal users within four weeks of deployment. The agentic platform was built using LangChain and LangGraph to provide a context-aware assistant for employees across the company.

How-ToDevelopers1 source

Demo: build voice agents with Google ADK, Gemini Live, LangSmith tracing

How-ToDevelopers1 source

LangChain: how to fix your doubled coding agent bill

LangChain explains why coding agent costs spiral out of control and how to trace, compare, and govern spend across Claude Code, Cursor, Copilot and more in one place.

LaunchAI Agents1 source

AgentOps generates multi-agent AI teams from plain English

How-ToAI Agents1 source

Deep Agents explained in new LangChain team video

AnalysisDevelopers1 source

LangChain builds ReviewBench benchmark for code review agents

ReviewBench evaluates code review agents by comparing their feedback against real PR comments from trusted human reviewers on actual pull requests.

AnalysisDevelopers1 source

Tool extracts bank statement data with YOLO, OCR, and LLM agents

LaunchDevelopers1 source

LangSmith introduces Align Evals for evaluator calibration

Align Evals, a new LangSmith feature, helps developers calibrate LLM evaluators to better match human preferences.

LaunchDevelopers5 sources

LangSmith LLM Gateway launches in public beta

LangSmith LLM Gateway is now in public beta: one gateway for spend and rate limits, fallback policies, and PII redaction before data reaches model providers, working across models and providers. Admins can set per-customer and per-user limits under a single API key, and BYOK support lets teams use existing provider contracts.

LaunchDevelopers1 source

LangChain Academy launches Certified Agent Engineer program

AnalysisDevelopers1 source

Max Agency podcast episode features Cognition President

EventDevelopers1 source

LangSmith Roadshow Atlanta features Home Depot engineer on production agents

AnalysisDevelopers2 sources

How Similarweb Evaluates Agent Reports with LangSmith

Similarweb evaluates long-form agent research reports using LangSmith's rubrics, faithfulness checks, traces, and baseline comparisons.

How-ToDevelopers1 source

LangChain Academy launches course on autonomous agent improvement

EventAI Agents1 source

En route to improving your agents

How-ToDevelopers3 sources

LangChain data agent scales request volume by 40x

EventDevelopers1 source

LangChain hosts agent development workshops at Ai4 2026

AnalysisDevelopers1 source

CreditGenie_US uses LangSmith to debug agent traces

LaunchDevelopers2 sources

Deep Agents v0.7.0b2 released with more performant, configurable harness

EventDevelopers1 source

Deep Agents extends support to leading open models

EventDevelopers1 source

Fireside chat on building AI SRE in production with Traversal AI

AnalysisDevelopers1 source

Bridgewater builds AIA Pocket Analyst Tool using LangChain

AnalysisDevelopers1 source

LangChain revamps Deep Agent benchmarking

New eval setup covers coding, conversation, and retrieval tasks. Used in Harbor to measure performance before shipping changes.

AnalysisDevelopers1 source

LangChain: Lower inference costs enable specialized agent workflows

EventAI Agents1 source

Webinar on improving AI agent production loops announced

EventDevelopers2 sources

LangChain and Cognition host meetup on LLM Wikis and OpenWiki

LaunchDevelopers3 sources

Eval Engineering Skill: Build Evals From Repo Context and Traces

LangChain's Eval Engineering Skill inspects an agent's repo and traces to propose evals via user interviews, outputting runnable Harbor tasks. It aims to automate the evaluation engineering workflow.

LaunchDevelopers1 source

dcode adds native browser control with /goal command

AnalysisDevelopers1 source

LinkedIn cuts time-to-interview by 60% with LangGraph hiring agent

EventDevelopers1 source

Apollo.io cuts dev-to-launch by 80-85% using Deep Agents

AnalysisDevelopers1 source

How Apollo Uses Deep Agents and LangSmith for GTM AI

Apollo leverages LangChain's Deep Agents and LangSmith to power an AI assistant for the full GTM loop: prospecting, enrichment, outreach, analytics, and MCP integrations. The case study details how Apollo rebuilt its AI assistant using these tools to improve efficiency.

LaunchDevelopers3 sources

LangSmith launches tracing for voice agents

LangSmith now supports tracing for voice agents built with Pipecat, LiveKit, OpenAI Realtime, and Gemini Live. Captures audio, STT/TTS latency, interruptions, and tool calls in a single trace.

LaunchDevelopers1 source

Tracing plugin connects Cursor AI agents to LangSmith

EventDevelopers1 source

LangSmith Summer AMA series covers agent development lifecycle

EventDevelopers3 sources

Panel: Single AI agent conversation can look flawless but still be broken

At VB Transform 2026, LangChain's Harrison Chase and leaders from Conviva and CoreWeave argued that perfect single-agent conversations can mask broken products. They advocated moving from scoring individual traces to comparing user cohorts against baselines.

AnalysisAI Agents4 sources