KubeCon + CloudNativeCon Europe 2025

LLMs can provide a quick injection of magic into an existing product (or product concept)! Most of us looking to build on LLMs aren't ML engineers or AI experts, after all, and this new wave of LLM offerings makes it easy for any of us to build something delightful.

But once that product or feature is shipped, in production, in front of users, the problems all collapse back into something that feels awfully familiar: performance challenges, questionable accuracy, and unhappy or confused users.

This talk will assert that building on LLMs is just like buliding on top of any other sort of black box in our architecture (APIs, DBs, etc)—this one just happens to be inherently unpredictable and probablistic.

We'll cover how to leverage observability best practices (like SLOs!) in this highly parameterized and rapidly evolving world, with nondeterministic outputs and a bunch of perceived risks—and you'll emerge more confident and ready to deal with this new AI-driven world.