Arize Builders Meetup - London
Join Arize AI for an evening of technical talks and networking in London. Whether you're building AI agents, fine-tuning models, or operating LLM applications in production, connect with fellow builders pushing the industry forward. Hear firsthand lessons from teams shipping agentic systems and production LLM workflows today — from evaluation and observability to reliability and scaling — then stick around for drinks and conversation with the community.
📍 London (register to see exact location)
🍕 Food and drinks will be provided
—
AGENDA
6:00 - 6:30 PM — Check-in & Welcome Reception
6:30 - 7:00 PM — Optimizing Skills and Tools, with Vision and GEPA for fun and profit
Shaun Smith, MCP/Open Source, Hugging Face
A practical guide on getting started with GEPA to improve performance with big and small models.
7:00 - 7:30 PM — Lessons from Building a Real-World Adverse Media Pipeline
Adam Hill, Data Scientist, ComplyAdvantage
LLMs are magical, until they aren’t. Extracting adverse media entities might sound straightforward, but throw in hallucinations, inconsistent outputs, and skyrocketing API costs, and suddenly, that sleek prototype turns into a production nightmare.
Our adverse media pipeline monitors millions of articles a day, sifting through vast amounts of news to identify reports of crimes linked to financial bad actors, money laundering, and other risks. Thanks to GenAI and LLMs, we can tackle this problem in new ways, but deploying these models at scale comes with its own set of challenges: ensuring accuracy, controlling costs, and staying compliant in highly regulated industries.
In this talk, we’ll take you inside our journey to production, exploring the real-world challenges we faced through the lens of key personas you will find in every business. Expect practical insights, cautionary tales, and real-world lessons on making LLMs reliable, scalable, and production-ready.
7:30 - 8:00 PM — Stop Paying for Frontier Models
RL Nabors, Developer Relations, Arize AI
Most teams default to frontier models for every AI task, but many workloads can be handled faster, cheaper, and more privately with smaller local models. In this session, RL Nabors, former Meta React core team member and AWS alum, shares a practical framework for deciding when to use frontier models versus local alternatives.
You'll learn the key concepts behind model evaluation, including capability evals, golden datasets, and LLM-as-judge, and see real-world examples spanning agentic systems, moderation, and generative summarization. RL will demonstrate how to build evaluation workflows from your own production traces and use results to improve prompts, validate performance, and ship with confidence.
8:00 - 9:00 PM — Happy Hour & Networking
Hosted by Arize AI