Building Engine v2: How LangChain approaches agent improvement
LangSmith Engine v2 automates agent development, offering validated fixes, red teaming, and cross-trace analysis to improve AI agents before production.
Read articleTopic
Agent Engineering
All digests tagged Agent Engineering
Suggested route
Topic journey
Move from earlier context through the available material to the newest signals. This route is a reading aid, not a difficulty ranking.
Start here
Build a secure computer for your agent 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.Build context
The Art of Loop Engineering: How to Build Agents That Improve Over Time 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.Recent signals
Building Engine v2: How LangChain approaches agent improvement LangSmith Engine v2 automates agent development, offering validated fixes, red teaming, and cross-trace analysis to improve AI agents before production. How To Build A Harness With Jev | A LangChain x TypeSafe Conversation Jev is a System 1 model that makes fast, structured decisions without generating text. Learn how to integrate it into agent harnesses for safety classification and model routing, significantly improving efficiency and reliability. Create an agent that can browse the web with Managed Deep Agents and Browserbase's Stagehand We're going to use LangSmith managed deep agents and Stagehand V4 tools. This allows us to build an agent that can interact with web pages by scrolling, clicking, and navigating across pages.
How To Build A Harness With Jev | A LangChain x TypeSafe Conversation
Jev is a System 1 model that makes fast, structured decisions without generating text. Learn how to integrate it into agent harnesses for safety classification and model routing, significantly improving efficiency and reliability.
Read article
Create an agent that can browse the web with Managed Deep Agents and Browserbase's Stagehand
We're going to use LangSmith managed deep agents and Stagehand V4 tools. This allows us to build an agent that can interact with web pages by scrolling, clicking, and navigating across pages.
Read article
The Art of Loop Engineering: How to Build Agents That Improve Over Time
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
Build a secure computer for your agent
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