Channel
Digests from LangChain
Managed Deep Agents simplifies agent deployment by bundling the Deep Agents harness with infrastructure like Context Hub and durable execution, enabling seamless transition from local code to production scale.
Read article
Harmonic quadrupled user retention by shifting from brittle query graphs to Deep Agents. Learn how a model-plus-tools loop and file system abstractions solve context overload.
Read article
Deep Agents are defined as a sophisticated 'harness' built around foundational LLMs, providing necessary infrastructure—memory, tools, file systems, and middleware—to make agents reliable for production use.
Read article
The industry is shifting focus from training bigger models to optimizing cost and speed. Key techniques include the 'sidekick' agent architecture, which uses parallel processing of multiple LLMs for better price performance.
Read article
Building AI SRE agents requires overcoming petabyte-scale data challenges. Success hinges on creating a robust agent harness, building a production world model, and strategically balancing offline vs. online search.
Read article
PAT, an AI analyst tool built by Bridgewater Associates, treats agentic coding as a compiler problem. It uses LangGraph for state management, enabling parallel code generation and deterministic execution to perform deep research in minutes.
Read article
Learn Loop Engineering: The art of building reliable, self-improving AI agents. Discover how Core, Verification, Event-Driven, and Self-Improvement loops transform non-deterministic models into production-ready systems.
Read article
LangSmith Sandboxes provide a secure, isolated computer for agents. Using hardware virtualized microVMs and an O proxy, they enable running untrusted model-generated code at scale while maintaining strict security controls.
Read article
Mastering the Agent Development Lifecycle requires moving beyond demos to systematic iteration across Build, Test, Deploy, Monitor, and Govern. Learn how advanced tooling uses tracing and online evals to ensure agents behave reliably at scale.
Read article
dcode introduces the /goal command for long-running tasks. It establishes visible acceptance criteria and uses a 'goal loop' to guide agents over hours, allowing mid-run steering and inspection via LangSmith tracing.
Read article
Learn how LinkedIn built a hiring agent using LangGraph to cut time-to-interview by 60%. We cover the shift from static workflows to advanced plan-execute-replan loops and essential harness engineering techniques.
Read article
Learn how to trace every Cursor agent turn into LangSmith by installing the plugin, setting three environment variables, and running an end-to-end task.
Read article