First-party releases and research from LangChain. Headlines and excerpts link to the original articles.
LangChain's Managed Deep Agents v0.9 adds a reactions API that lets Slack agents set emoji responses dynamically, using a static string, a Python callable, or a decision model to build loading states and task acknowledgments.
Snyk built its customer-facing AI support agent, Snyk Assist, on LangChain, LangGraph and LangSmith, starting as an internal tool and reaching the core product on 1 September 2026. It has handled over 60,000 queries and resolves more than 85% of sessions without a support ticket.
LangChain released Restock, a sample agent running in Slack on Managed Deep Agents that searches products, builds a cart and pays through Stripe's Link wallet over the Machine Payments Protocol. Its sample code shows how to keep payment credentials and spending limits outside the model.
LangChain added three capabilities to skills in Deep Agents: binding tools to skills, pinning skills at runtime, and reloading skills mid-thread. Tool schemas stay out of context until the agent reads a skill, and pinned skills skip a read round trip.
LangChain released Managed Deep Agents v0.9 in public beta, adding agent-created schedules, per-run configuration of model, skills and tools, and Slack reactions that acknowledge messages before replies.
LangChain built a model router into Open SWE's harness that cut median cost per coding task by 64% with no measurable change in quality, according to an A/B test across 973 threads. The post describes how to build a similar router.
TypeSafe AI has released Jev, a System One model that makes structured classification decisions instead of generating text, and LangChain has published an integration guide for using it in agent loops. TypeSafe AI reports up to 200x faster inference and 400x lower cost than comparable LLMs on classification tasks.
LangChain announced that Jev, a System One model from TypeSafe AI, is now available as a judge for evaluations in LangSmith. The company says Jev returns typed answers instead of generated text and reported it was more accurate, consistent, faster and cheaper than several LLM judges in one internal test.
LangChain announced several LangSmith updates, including Engine v2 with red teaming and automated fix validation, Managed Deep Agents v0.8 with user-level memory and built-in web search, Trajectories, and LangSmith Fine-Tuning. The announcements were made at Interrupt NYC.
LangChain published a blog post describing how Jev, TypeSafe AI's decision model that returns structured answers instead of generated text, can be orchestrated with LangGraph. The post cites TypeSafe benchmarks of up to 200x faster and 400x cheaper performance on narrow decision tasks, and a document review demo where Jev was 5-6x faster than Sonnet at classification.
LangChain announced LangSmith Custom Apps, which allow teams to build, publish, and run custom interfaces on LangSmith agent data inside LangSmith, without handling hosting, authentication, or permissions. The feature is available on Plus and Enterprise plans, and LangSmith's Macaw design system is now open source.
LangChain announced LangSmith Engine v2, which adds Red Teaming for proactive agent issue detection and automated validation of proposed prompt and code fixes before human review. The release also expands detection to inefficient agent paths and trends in error rate, latency, and cost.
LangChain launched Trajectories in LangSmith, a chronological, conversational view of an agent session that aggregates messages from humans, AI, and tools across main agents and subagents. It is available now on all plans in the US, and trajectories can be scored with online evaluators and routed to annotation queues or datasets.
LangChain launched Managed Deep Agents 0.8, adding user-owned credentials, user-level memory, HTTP channels, file transfer in Slack, and a pre-built web search tool powered by Parallel. The release is in beta and web search is available free during that period.
LangChain launched LangSmith Fine-Tuning and smithtune, a CLI that turns agent trajectories stored in LangSmith into fine-tuned models, handling dataset creation, training via Fireworks or Baseten, and evaluation. It is available in Public Beta.
LangChain published a blog post describing how healthcare AI teams Abridge and Included Health use LangSmith to convert clinical review into reusable datasets, evaluators, and release gates. It cites Abridge cutting its release cycle from one to two months to days, and Included Health reporting a 75% engagement lift and flagging over 99% of high-risk situations.
LangChain tested TypeSafe AI's Jev as an agent evaluator against GPT-5.6 Luna, GPT-5.6 Terra, and Claude Sonnet 4.6, finding Jev matched the human oracle on all 500 binary decisions, had 92–913x lower quality-score variance, and cost $0.00035 per call. LangChain calls the results promising but early.
LangChain introduced Deep Life Sci, an open source agentic assistant for clinical and lab scientists, built on its Deep Agents harness. It accesses over 600,000 ClinicalTrials.gov studies, 29 million PubMed abstracts, and 12 million PubMed Central full-text articles, and uses LangSmith sandboxes for data analysis.
Included Health built Dot, an AI healthcare navigation agent, using LangGraph, Deep Agents and LangSmith, with a federated multi-agent architecture, human handoff and clinical oversight. Dot launched to clients in August, with a 75% lift in chat engagement and clinical audits finding over 99% of high-risk situations identified.
LangChain published a report on how Madrigal Pharmaceuticals, Abridge, and Vizient build AI agents in healthcare under stricter trust, audit, and patient-safety constraints, citing survey-style figures such as 76% naming tracing, evaluation, and spend visibility as prerequisites for autonomy.