New in LangSmith: an on-call copilot for triage, computer use in Fleet, voice traces, and more. Plus a new course on LangSmith Deployment, and upcoming events from Chicago to Vegas.
LangSmith Updates
🔔 Fleet On-Call Copilot
A prebuilt agent template that works through your code, traces, and runbooks to triage alerts and draft updates for your review.
💻 Computer Use in Fleet
Agents can now use an isolated virtual computer for code, files, and authenticated API calls.
▶️ New UI for Voice Traces
Debug audio faster with an inline audio player and see exactly which span was active at each moment.
📊 Experiment Status Tracking
See live progress for experiments started from the LangSmith UI or SDK.
💬 Native Slack Integration for LangSmith Engine
Send Slack notifications for Engine Issues.
Open Source
Deep Agents Rubrics
RubricMiddleware helps Deep Agents evaluate their own work and keep iterating until the task meets your criteria.
Programmatic Subagents
Dispatch subagents from interpreter code to fan out work and synthesize results.
⏯️ On-Demand: Harrison Walks Through the Agent Development Lifecycle
Harrison breaks down the four-phase agent development lifecycle (ADLC) — Build, Test, Deploy, and Monitor. You’ll learn how teams can catch failures earlier, turn production behavior into stronger evals, and improve agents without relying on guesswork.
🎙️ Max Agency Podcast: The best agents are simpler than you think
Zack Reneau-Wedeen, Head of Product at Sierra, reveals how and why the company is building agents that span the entire customer lifecycle, from browsing and booking to sales and loyalty.
ICYMI, watch our previous episode with Nick Larus-Stone, Head of AI at Benchling. Nick breaks down where the coding-agent playbook holds up for scientific work, and where it breaks down.
🎓 Speak the Lang
See our favorite use cases, best practices, and interviews covering the most top-of-mind topics in the AI space.
.png)
New Course: Introduction to LangSmith Deployment
Getting an agent to work locally is one thing; running it reliably at scale is another. Learn to deploy, manage, and control your agents with this course on LangSmith Deployment.
Tutorial: Add voice to LangGraph agents
Connect any LangGraph agent to audio without rebuilding your graph from scratch. This walkthrough covers setup, using Pipecat for voice conversation, and complete voice agent tracing with LangSmith.
Upcoming Events
🗽 June 29 // Chicago: LangChain + AWS Workshop
A hands-on session on Deep Agents, including how to integrate them with AWS services to ensure they are scalable, reliable, and enterprise-ready. RSVP →
🦾 July 16 // Berlin: LangChain Meetup - Building Great Agents
An evening with LangChain, Zalando, and DB Engineering & Consulting to explore how teams can build, evaluate, and operationalize agents in production. RSVP →
🏛️ July 30 // Washington DC: LangChain Community Meetup
Join us and G2X for a builder-focused LangChain meetup on using Deep Agents to solve complex GTM research workflows. RSVP →
🏎️ August 4 // Las Vegas: High Stakes, High Speed
Leave the latency on the grid and join LangChain, Elastic, and Google Cloud for F1 simulators, drinks, and the fastest networking in Vegas. RSVP →
⚙️ What teams are building with LangChain
Box accelerated agent improvement and iteration speed 3X with Deep Agents. See how Box built Box Agent to search, analyze, and synthesize enterprise content while preserving security, permissions, and model flexibility.
Read the story →
Harmonic 4X’d customer retention using LangSmith Deployment. How Harmonic rebuilt Scout, their AI for sourcing and researching startups, accelerating product iteration from months to days.
Read the story →
How can you follow along with the Lang Latest? Check out our Blog, Changelog, and YouTube channel for more updates.
For any additional questions or feedback, email us at hello@langchain.dev.
