How to Build Proactive, Always-On Agents with the Schedules SDK in Managed Deep Agents
Most proactive agents run on a simple cron. Learn what scheduled runs unlock, from memory to smart triage, and how to add them to Managed Deep Agents.
Most proactive agents run on a simple cron. Learn what scheduled runs unlock, from memory to smart triage, and how to add them to Managed Deep Agents.
LangChain used OpenWiki, its open-source wiki compiler, and an evidence graph to build a persistent memory layer that preserves knowledge for agents to reuse across tasks. Learn how.
How LangChain built Content Studio, an open-source design agent in Slack that makes on-brand videos, graphics and decks, and the harness that powers it.
Learn how LangChain built internal agents across marketing, sales, and engineering, and how they have completely changed how those teams work.
Agents waste time and context on clumsy searches, oversized results and stale data. Learn the retrieval techniques LangChain's Deep Agents harness uses to get the right context in.
Numan built an AI health coach named Nu using LangGraph and LangSmith, incorporating per-category evaluations, simulated conversations, and safety measures.
LangChain's October 2026 newsletter highlights new releases from Interrupt NYC & London, including LangSmith AI Search, Engine v2, Trajectories, Custom Apps, Fine-Tuning, and Managed Deep Agents v0.9.
LangChain answers common questions about agent evaluations, covering evaluator types, LLM judges, and cost reduction.
LangChain discusses context engineering for long-running agents using techniques like offloading, summarization, and subagents.
Orange Business used LangChain and LangSmith to build Live Intelligence, a platform for agents with governance, evals, observability, and production scale.
Open SWE, built on Deep Agents and LangGraph, provides the core architectural components for internal coding agents.
Harness engineering improved LangChain's coding agent from Top 30 to Top 5 on Terminal Bench using self-verification, tracing, and context optimization.
LangChain used the Deep Agents CLI to automate migrating code samples into testable, CI-ready examples, addressing the problem of stale code snippets in documentation.
The Deep Agents SDK manages context for long-running AI tasks by preventing context rot through offloading, summarization, and filesystem abstraction.
Open models like GLM-5 and MiniMax M2.7 now match closed frontier models on core agent tasks, operating at a fraction of the cost and latency.
LangChain launches Deep Agents deploy in beta, offering a fast way to deploy model-agnostic, open-source agent harnesses.
AI Search in LangSmith allows querying traces using natural language by describing the behavior you're looking for to retrieve relevant trace data.
Use ScaleDown's constrained decoding models with LangChain and Deep Agents to summarize history, compress tool results, and extract data faster and cheaper.
Managed Deep Agents introduces an API for managing distributed agent reactions and dynamically assigning emoji responses.
Snyk transformed an internal support agent into Snyk Assist, a customer-facing AI feature powered by LangChain, LangGraph, and LangSmith.
LangChain introduces agents that can make real purchases using Stripe's Link and Managed Deep Agents.
Deep Agents now allows tools to be bound to skills, skills to be pinned at runtime, and skills to be reloaded mid-thread, maintaining context efficiency.
LangChain has released new capabilities in Managed Deep Agents, allowing agents to schedule follow-ups, reconfigure themselves on each run, and react to Slack messages.
LangChain presented a new method for building a model router, which reduced the median cost per coding task by 64% with no measurable drop in quality.
LangChain provided a guide to TypeSafe AI's System One model, known as Jev, explaining its function, fit in agent loops, and use with LangChain.
Jev is now available as a judge for LangSmith Evals, providing faster and cheaper structured feedback on agent traces.
LangGraph demonstrates orchestrating Jev, TypeSafe AI's decision model, to build faster, cheaper production agents.
LangChain announced new updates to LangSmith, including Engine v2 with red teaming and automatic testing, a new version of Managed Deep Agents, trajectories, and more.
LangSmith Custom Apps allows users to build custom interfaces around their LangSmith data, publish them to their workspace, and bypass hosting, authentication, and permissions work.