Everything That Can Go Wrong Building Analytics Agents (And How We Survived It) - AI Engineer Paris скачать в хорошем качестве

Everything That Can Go Wrong Building Analytics Agents (And How We Survived It) - AI Engineer Paris

Text2SQL demos work great until real users show up. Then your agent finds 47 different customer tables, hallucinates metrics that don't exist, and confidently tells the CEO that churn is -40% (which would be impressive if it weren't completely wrong). I am part of the team that builds Metabot - an AI assistant that lives inside Metabase to help users answer their own data questions without bothering the analytics team. Simple goal, right? Turns out teaching an AI to navigate real organizational data is like teaching someone to drive in a city where all the street signs are wrong and half the roads don't exist on any map. This talk is your field guide to the chaos we've encountered. We'll share the specific disasters that taught us hard lessons: why your pristine demo data means nothing, how users will find every edge case you never considered, why business rules written nowhere will break everything, and how "temporary" tables from 2019 somehow become production dependencies. You'll walk away with battle-tested strategies for building analytics agents that survive contact with real organizations: practical approaches to data documentation, designing agent tools that won't spectacularly backfire, and building guardrails that actually work when chaos strikes. This isn't a sales pitch disguised as a tech talk - it's a real field guide to the beautiful disaster of production AI systems. Speaker: Thomas Schmidt, AI Engineer, professional collector of Text2SQL disasters and data warehouse horror stories, Metabase