MIAMI: Evals 102 LangChain Community Meetup

​Join us in Miami on April 2, 2026 for an evening of LangChain insights, AI talks, and community connections hosted at Co-Work LatAm, Brickell 🎉

​Evals 102 picks up where the basics left off. Expect a practical, no-fluff deep dive into advanced evaluation patterns for AI agents from using your coding agent as a meta-evaluator to rethinking how you build and manage datasets in production!! Whether you're running RAG pipelines, scaling LLM-powered applications, or trying to move beyond "vibe checks" and into rigorous agent testing, this night is for you 🚀

​🎙️ Speakers

• ​Andres Torres — LangChain Ambassador | Lead AI Architect & Strategy @ NCLH

• ​Camron Haider — Senior AI Engineer @ NCLH

​Why Attend?

• ​See how LangChain and LangSmith are used in real-world production AI systems

• ​Learn advanced eval patterns — meta-evaluators, capability datasets, regression datasets, and when to skip formal judges entirely

• ​Understand how to wire coding agents into your evaluation loop to 10x your iteration speed

• ​Connect with the Miami AI/ML community — engineers, researchers, and builders

• ​Enjoy food, drinks, and great conversations

​📅 Agenda / Schedule

• ​6:00–6:30 PM — Registration & Networking

• ​6:30 –7:30 PM — Talk (Evals 102: Let Your Agent Do the Hard Parts)

• ​7:30–8:30 PM — Networking

​👤 Who Should Attend?

​ML engineers, AI developers, data scientists, and software engineers working with LangChain, LangSmith, LLMOps, RAG, and agent evaluation. Also welcome: anyone curious about building production-grade AI applications and moving beyond ad hoc testing into real eval workflows.