The latest AI news and updates of LangChain — AI company building frameworks and observability tools for developing and orchestrating LLM agents. Covering LangChain's latest product updates, company news, and launches from the past 90 days.
LangChain19h agoLangChain’s internal data agent now handles roughly 40x the request volume of its three-person data team. This shift redirects the team to focus on building the models, business context, and guardrails that ensure agent reliability. The company’s agent-first data stack integrates Hex, dbt, and semantic models to provide trusted, self-serve analysis across the organization.
LangChainJul 27LangChain’s LangSmith Insights feature now converts production agent traces into targeted test questions. CreditGenie used this capability to generate 100–200 test questions per behavior after debugging thousands of agent traces. This workflow automates the creation of evaluation datasets directly from real-world production data, helping teams identify and resolve agent failures more efficiently.
LangChainJul 27LangChain released Deep Agents v0.7.0b2, reducing default-agent input tokens by 65% compared to v0.6.12. The update introduces in-place middleware overrides, replacing built-in instances with custom settings without disabling defaults. Additionally, planning todos are now opt-in, requiring explicit restoration via middleware configuration.
LangChainJul 24Bridgewater Associates presented PAT, an internal AI analyst deployed to hundreds of investors that performs hours of deep exploratory research in minutes. The tool leverages proprietary data and methodologies, featuring per-user security, autonomous self-correction, and parallel code generation. PAT operates as a component of Bridgewater’s artificial investor, executing complex analytical investigations through a compiler-like agentic architecture.
LangChainJul 22LangChain launched the Eval Engineering Skill to help coding agents build evaluation tests. The skill generates evals by analyzing context from a code repository and agent execution traces. This provides a measurable way to assess agent performance and reliability using production data from the development lifecycle.
LangChainJul 22LangChain highlights a community-developed extension that adds native browser control to its dcode coding agent. The implementation uses the agent’s /goal command to define objectives for browser-based tasks. This capability allows the agent to interact with web interfaces directly, expanding its utility for complex, multi-step engineering workflows.
LangChainJul 22LinkedIn engineers detailed their hiring agent at LangChain’s Interrupt conference, which uses LangGraph to cut time-to-interview by 60% for small businesses. The agent employs a central planner with a plan-execute-replan loop and a context-driven human-in-the-loop design to manage stateless scalability and ensure consistent recruiter-facing action paths.
LangChainJul 21Apollo.io rearchitected its AI Assistant using LangChain’s Deep Agents, reducing dev-to-launch time for new skills by 80-85%. The new skill-based architecture replaces a rigid supervisor system with dynamic goal-based execution. Apollo also introduced AI Watchtower, a six-layer evaluation framework, and expanded the assistant into a headless agent accessible via API and MCP server.
LangChainJul 21LangChain launched LangSmith tracing for voice agents built with Pipecat, LiveKit, OpenAI Realtime, and Gemini Live. The integration captures conversation audio, speech-to-text and text-to-speech latency, voice activity detection events, and interruptions. This provides full observability into voice pipelines, allowing teams to debug errors and evaluate agent behavior in production using the same workflows as text-based agents.
LangChainJul 21LangChain released a tracing plugin for Cursor that captures agent sessions, including model runs, tool calls, subagent activity, and file attachments, directly into LangSmith. The plugin uses the coding-agent-v1 schema, providing a unified dashboard for monitoring and comparing agent performance across Cursor, Claude Code, and Codex.
LangChainJul 18LangChain released Open SWE, an open-source, cloud-hosted coding agent that autonomously plans, writes, tests, and reviews code. The system integrates directly with GitHub, allowing tasks to be triggered via issue labels. It uses a multi-agent architecture with dedicated planner and reviewer components to execute complex engineering tasks in isolated sandboxes without requiring local resources.
LangChainJul 16LangChain details three middleware features powering the Box Agent. Parallel citation generation streams answers without user interruption, while prompt caching reduces latency and costs in multi-turn conversations. Additionally, the system automatically summarizes conversation history exceeding 170,000 tokens to prevent context overflow, ensuring the agent maintains performance at enterprise scale.
LangChainJul 15LangChain published a conceptual guide detailing the requirements for governing AI agents in production environments. The guide advocates for isolated, hardware-virtualized sandboxes to ensure safe execution, credential management, and full auditability. It outlines four core primitives for agent environments, including microVM isolation and snapshot-based state persistence, to help teams manage access, protect data, and control costs.
LangChainJul 15LangChain now allows one-click deployment of Fleet agents into Slack. Each agent receives a custom identity, name, and icon, enabling it to participate in channels and threads. The integration supports file handoffs and human approval workflows directly within Slack, keeping project context and agent interactions in one place without requiring code.
LangChainJul 15Toyota’s enterprise AI team built ToyotaGPT, a platform powered by LangGraph that reduced agent delivery from six months to four days. The system supports over 50 agents in production, utilizing a unified tool layer and automated skill generation from unstructured data. This architecture deploys agents via configuration files, replacing manual engineering workflows.
LangChainJul 14LangChain updated LangSmith to provide full-session observability for Cursor, GitHub Copilot, Pi, and OpenCode coding agents. The platform captures the complete run tree, including model calls, tool usage, and subagent activity, with no extra instrumentation required. It also provides out-of-the-box token usage and cost tracking, allowing teams to query and compare agent performance across different coding tools.
LangChainJul 10LangChain built an agent that drafts a cited VC investment memo in about 90 seconds for $0.40 in API costs. The agent uses four parallel LangGraph nodes powered by the Perplexity Agent API to research financials, product, and market data. A tool-less synthesizer then compiles the findings into an auditable memo with primary source citations for every claim.
LangChainJul 10LangChain published a playbook detailing how to tune agent harnesses for NVIDIA’s Nemotron 3 Ultra. By optimizing system prompts and middleware, the agent achieved a 0.86 score on the Deep Agents suite, nearly matching Opus 4.8 at roughly 10x lower cost per run. This eval-driven approach improves agent performance without requiring model fine-tuning.
LangChainJul 10LangChain updated OpenWiki to support general-purpose memory via a new brains mode. This mode builds a local personal wiki from sources like Gmail, Notion, X, and web search, separate from the tool's existing code-documentation mode. Each mode uses distinct setup and update workflows to maintain agent-readable knowledge layers for different work contexts.
LangChainJul 9LangChain highlights Finch Legal, an AI-powered pre-litigation platform for personal injury firms that has grown 10x over the past year. Finch uses LangSmith as its production observability layer to trace, evaluate, and monitor quality and cost across workflows including client communications, medical-record follow-up, and document processing.
LangChainJul 9LangChain released a plugin that traces every Claude Code session directly into LangSmith. The setup requires three commands and one JSON block, taking approximately two minutes to complete. Once configured, the plugin captures all messages, tool calls, and subagent runs as inspectable traces, providing full observability for debugging agentic coding workflows.
LangChainJul 8LangChain and NVIDIA launched the NemoClaw Deep Agents Blueprint, an open reference architecture for building governed enterprise agent systems. The stack integrates Nemotron 3 Ultra, a tuned Deep Agents harness, and the OpenShell runtime. In evaluations, the blueprint achieved an aggregate score of 0.86 at a cost of $4.48 per run, roughly 10x lower than comparable models.
LangChainJul 7Schneider Electric runs over 60 AI agents in production across 100+ countries, all traced through self-hosted LangSmith. Their internal AI Assistant, One Jo, serves 160,000 employees. The company uses LangSmith’s observability, evaluation, and deployment pillars to manage these agents within strict data residency and cybersecurity controls.
LangChainJul 6LangChain introduces LangSmith Evaluation to assess AI agent performance using real production data. The platform identifies agent failures and quality issues by running evaluations before and after deployment. It supports human feedback, prompt optimization, and CI/CD integration to catch regressions and improve agent reliability throughout the development lifecycle.
LangChainJul 2LangChain updated LangSmith to provide unified tracing for Claude Code, Codex, Cursor, GitHub Copilot, Pi, and OpenCode. The platform normalizes logs from these tools into a consistent trace tree, metadata schema, and query syntax. This integration provides a single dashboard for monitoring and comparing agent activity and costs across multiple coding tools.
LangChainJul 1LangChain launched OpenWiki, a CLI tool that writes and maintains codebase documentation specifically for AI agents. It generates repository documentation, automatically updates it via GitHub Actions, and supports Q&A over the codebase. The tool also appends instructions to AGENTS.md and CLAUDE.md files to ensure coding agents reference the documentation during development.
LangChainJul 1LangChain added support for recursive language model (RLM) workflows to its Deep Agents framework. This inference strategy allows agents to recursively call themselves or sub-models to decompose complex tasks before finalizing an answer. The implementation uses CodeInterpreterMiddleware to improve reasoning accuracy on long-context problems, as demonstrated in performance comparisons against standard agents on the Ulong dataset.
LangChainJul 1Z.ai's GLM-5.2 model is now accessible in the dcode coding agent. Developers can connect the open-weights model in three steps: download dcode, select GLM-5.2, and add an API key. The integration brings frontier performance on open weights to agentic coding workflows without model hosting overhead.
LangChainJul 1LangChain reports that Pendo catches 60% of agent failures in its product agent, Novus, before they reach customers. The team uses the LangSmith trace dashboard to identify gaps between customer needs and agent performance, then creates new evaluation sets to resolve issues. This daily workflow turns production traces into proactive agent improvements.
LangChainJun 30LangChain introduced a code interpreter for Deep Agents that executes untrusted code using WebAssembly and QuickJS. This in-process isolation model constrains agent capabilities without requiring a full sandbox environment. The company also open-sourced the quickjs-rs runtime and langchain-quickjs middleware to enable secure, snapshot-based durable pauses for agent workflows.
LangChainJun 30LangChain integrated its Deep Agents, LangSmith Sandboxes, and LangSmith Observability into the Harbor evaluation framework. This unified stack runs agents in isolated, parallel cloud sandboxes while recording step-by-step traces and experiment results. The integration uses the --agent langgraph and --plugin langsmith flags to orchestrate agent trials with deterministic verification.
LangChainJun 25LangChain distinguishes between two agent patterns in its Fleet platform. General Purpose Chat handles ad-hoc, low-setup tasks that end when the answer arrives. Specialized Agents manage recurring work by providing durable instructions, scoped tools, persistent memory, and event-based triggers. This framework allows teams to graduate one-off tasks into repeatable, delegated responsibilities as patterns emerge.
LangChainJun 22LangChain released Deep Agents v0.6, introducing a code interpreter that lets agents execute tool calls programmatically within a runtime. By keeping intermediate results in the runtime state and returning only relevant output to the model, this feature reduces round trips and token consumption. It enables model-agnostic programmatic tool calling and recursive workflows for any agent.
LangChainJun 22LangChain identifies two conflicting requirements for production-grade agent sandboxes: the instant startup speed of serverless functions and the statefulness of full machines. LangSmith Sandboxes address this by using hardware-virtualized microVMs that allow agents to install dependencies, edit files, and persist state across sessions. This architecture provides isolated environments for executing untrusted, model-generated code without exposing host infrastructure.
LangChainJun 18LangChain added LangSmith sandboxes as a first-class environment in the Harbor evaluation framework. The integration enables agent evaluations on LangSmith infrastructure via the harbor[langsmith] package and a LangSmith API key. It supports Dockerfile snapshotting, SDK profile switching, and a full execution lifecycle, joining existing sandbox providers like Daytona, E2B, and Modal.
LangChainJun 18LangChain Labs fine-tuned a Qwen-3.5-35B model to detect perceived errors in production agent traces. The fine-tuned model matches or exceeds frontier model performance, achieving 96.1% accuracy on test datasets while running 10-100x cheaper than frontier alternatives. LangChain is rolling out this judge to select customers over the coming weeks before a broader release.
LangChainJun 17LangChain introduced On-Call Copilot, a new agent template for LangSmith Fleet that automates incident response. The agent triages incoming alerts, investigates root causes across code and traces, and manages ticket routing. It continuously learns from existing runbooks, escalation rules, and noise patterns to improve incident handling over time.
LangChainJun 15LangChain listed its LangSmith agent engineering platform as a fully managed SaaS on the AWS Marketplace. The integration supports deployment on AWS infrastructure, including Amazon EKS and S3, alongside deep connections to services like Amazon Bedrock and SageMaker. Pre-committed AWS spend now applies toward procuring the platform for building, testing, and observing AI agents.
LangChainJun 15LangChain deployed its LangSmith LLM Gateway internally to manage rising coding agent costs. The system enforces budgets across organizations, workspaces, users, and API keys, routing calls from tools like Claude Code and Codex. This centralized control provides real-time spend visibility and prevents runaway usage, maintaining budget predictability while allowing continued agent-driven development.
LangChainJun 15Box Agent now uses LangChain's Deep Agents framework to search, synthesize, and analyze enterprise content. The architecture employs a parent-child agent model to handle complex tasks like multi-document synthesis and structured report generation. It operates within Box's existing security and permissions model, ensuring agents only access content authorized for the specific user.
LangChainJun 15LangChain launched LangSmith Engine, an agent that monitors production traces to identify and resolve agent failures. Engine clusters related issues, writes prompt or code fixes, and can open GitHub pull requests for review. It also automatically suggests online evaluators and offline datasets to prevent recurring errors, building a feedback loop from production failures to agent improvements.
LangChainJun 15LangChain has integrated its Deep Agents orchestration framework and LangSmith observability platform into the Nebius Agents Blueprint. This open reference architecture provides a composable stack for building, operating, and continuously improving AI agents in production. The blueprint includes runnable recipes and cloneable code to help teams transition agent systems from prototypes to reliable, measurable production environments.
LangChainJun 10LangChain introduced Managed Deep Agents in private beta, an API-first hosted runtime for its open-source Deep Agents. This offering aims to streamline the operational complexities of deploying autonomous AI agents, allowing developers to focus on agent behavior rather than managing infrastructure.
LangChainJun 10LangChain is experimenting with interpreter skills, an extension to its agent skills that allows developers to embed TypeScript modules directly within a skill. This enables AI agents to execute complex, multi-step tasks with predictable, code-driven workflows. The update enhances reliability and evaluation beyond instruction-based guidance.
LangChainJun 9LangChain's LangSmith Engine now automatically proposes three resolution actions for every agent issue it identifies: opening a Pull Request (PR), creating a custom online evaluator, and adding failing traces to an offline evaluation suite. This aims to accelerate the agent development lifecycle by automating issue diagnosis and fix validation.
LangChainJun 9LangChain's LangSmith Fleet now supports direct file interaction, allowing AI agents to create and edit documents, presentations, and webpages. This update enables agents to generate new content or collaboratively edit existing files directly within conversations, streamlining content workflows.
LangChainJun 7LangChain now enables developers to deploy Google Agent Development Kit (ADK) agents directly to LangSmith. This integration provides built-in session persistence, streaming, and tracing for ADK agents on LangSmith's managed infrastructure. It simplifies moving ADK-built agent prototypes into production environments.
LangChainJun 7LangChain has released Deep Agents v0.6, introducing a Streaming feature that supports highly parallelized AI agent systems. This update enables real-time progress tracking for tools and subagents, addressing a key challenge in observing complex multi-agent workflows.
LangChainJun 7LangChain has updated its LangSmith Fleet platform to support shareable skills for AI agents. This allows domain experts to codify specialized knowledge once, ensuring consistent, up-to-date information is accessible and usable by all agents across a team without manual coordination. The update helps prevent knowledge silos and accelerates agent development by centralizing expertise.
LangChainJun 7LangChain Labs and Harvey published a study demonstrating how to significantly reduce the cost of LLM-as-judge verifiers for AI agents. Their research shows that batching verifier calls and using open-weight models can cut costs by up to 1,000 times. This makes it more practical to run extensive experiments and accelerate the iteration cycle for agent development, especially in complex domains like legal work.
LangChainJun 7LangChain launched LangSmith Sandboxes, ephemeral microVM-based environments for running agent-generated code. The platform handles orchestration, achieving a 0.98-second median spin-up time and scaling to thousands of concurrent instances. These isolated runtimes allow agents to install packages and execute code without exposing host infrastructure, with an integrated Auth Proxy managing outbound credential injection.
LangChainJun 7LangChain introduced Managed Deep Agents in private beta, offering a hosted runtime for deploying deep agents with durable execution and integrated observability. This aims to simplify the operational challenges of running autonomous AI agents in production, allowing developers to focus on agent behavior rather than infrastructure.
LangChainJun 7LangChain launched LangSmith LLM Gateway in private beta, a runtime governance layer for AI agents. The gateway sits between agents and LLM providers to enforce spend limits and redact PII or secrets before requests reach the model. Policy violations surface as traceable events directly within LangSmith, allowing investigation and remediation on the same surface where agents are built.
LangChainJun 7LangChain announced immediate support for NVIDIA Nemotron 3 Ultra, an open frontier model designed for long-running AI agents. This integration makes the model's 5x faster inference and up to 30% lower cost for complex agentic tasks directly available to developers using the LangChain framework.
Frequently asked questions