LangChain Boston Meetup: Loop Engineering and Open Models

Join us for an evening in Boston (Harvard Square) with Sydney Runkle and Mason Daugherty from the OSS team at LangChain. We will feature two talks on what it actually takes to make agents reliable in production.

🎤 Talk 1: The Art of Loop Engineering with Sydney

Getting agents to do valuable work reliably takes more than a good model — it requires a carefully designed harness. Sydney will break that harness down into a stack of four loops; she'll also cover where human oversight earns its place in each loop, and how primitives instrument the whole stack.

🎤 Talk 2: Why Open Models Have Crossed a Threshold with Mason

Open models like GLM 5.2 and MiniMax M3 now match closed frontier models on core agent tasks — file operations, tool use, and instruction following — at a fraction of the cost and latency. Mason will go over what our evals show and how to start using them in Deep Agents.

Agenda ⏰

6:00 PM: Welcome + Refreshments

6:30 PM:  Presentation with Sydney - The Art of Loop Engineering

6:50 PM: Q&A Session with Sydney

7:00 PM: Presentation with Mason - Why Open Models Have Crossed a Threshold

7:15 PM: Q&A Session with Mason

7:25 PM: Networking

8:30 PM: Event Ends

Event info:

🎤 Please note this event is fully in-person and will not be live-streamed or recorded.

📍 Location: Harvard Square — Address provided upon approval.

🎟️ We can only admit guests with approved registrations.

About the host:

LangChain powers the full agent development lifecycle — building, testing, deploying, and monitoring — so AI teams can improve their agents systematically. LangSmith Engine accelerates this cycle, automatically surfacing and fixing issues to improve agents over time. LangSmith is neutral by design, so teams can customize their own stack to optimize on cost and performance as the landscape evolves. More than 7,000 customers, including Nvidia, Bridgewater, LinkedIn, Workday, Harvey, and Rippling trust LangSmith to build and manage their agents. Learn more: www.langchain.com