Join us for the next Vibe Coding Meetup, hosted by Sam Silver with guest speaker Jonathan Seller, as we explore how to evaluate LLM performance.
Building with LLMs is one thing — knowing whether they’re actually performing well is another. This session will look at practical approaches to evaluating outputs, measuring performance, and building more reliable AI applications.
This session will include technical content and is particularly relevant for developers and builders working with LLMs, RAG, and AI-powered applications.
Come ready to learn, ask questions, and connect with others building with AI.
Speaker: Jonathan Seller
Jonathan Seller is a software developer with 25 years of experience building technology at startups and scale-ups. Now working on developing a RAG system at a big data company, and experiencing firsthand the transformation AI is bringing to development.
Mar
11
Thu
Halifax - Agentics Foundation Meetup
Autonomous AI in Practice: From Curiosity to Capability Agentic AI is no longer a theory experiment or a lab curiosity. It’s becoming a practical way to build systems that plan, decide, act, and adapt, with real autonomy.
Learn moreFeb
11
Thu
Halifax - Agentics Foundation Meetup
Autonomous AI in Practice: From Curiosity to Capability Agentic AI is no longer a theory experiment or a lab curiosity. It’s becoming a practical way to build systems that plan, decide, act, and adapt, with real autonomy.
Learn moreJan
14
Thu
Halifax - Agentics Foundation Meetup
Autonomous AI in Practice: From Curiosity to Capability Agentic AI is no longer a theory experiment or a lab curiosity. It’s becoming a practical way to build systems that plan, decide, act, and adapt, with real autonomy.
Learn moreDec
9
Wed
Halifax - Agentics Foundation Meetup
Autonomous AI in Practice: From Curiosity to Capability Agentic AI is no longer a theory experiment or a lab curiosity. It’s becoming a practical way to build systems that plan, decide, act, and adapt, with real autonomy.
Learn more