QA meets AI: Quality Engineering in the Age of AI

Welcome to another DevQOps meetup. Join us and enjoy three inspiring talks (in English) about Quality Engineering in the age of AI.
We will serve something to eat and refreshments, and there will be some time for mingle between the talks.

TALKS
1. Claes and Fredrik: When AI Writes the System - How can we trust it?
A thought experiment on what happens to quality, trust, and architecture when AI starts writing large parts of our systems — and how we might design and test for that future.
2. Olle Pridiuksson: AI agents that generate code and AI agents that test it - How we use AI at QA.tech
Multiple daily live-deploys with multiple levels of AI at all stages - let's talk how we use Cursor, Claude and our own AI agents to develop a complex SaaS, used by big customers such as Nordea or Visma. Basically, this will be a demo of how we use QA.tech in development of QA.tech.
3. Vilhelm von Ehrenheim: Evaluating Agents and LLM Chatbots - What to Measure When You Can't Predict the Output
Traditional testing assumes deterministic behavior. Give input X, expect output Y. AI systems break this model. The same prompt can produce different responses. "Correct" is subjective. And the system changes with every model update. This talk covers practical approaches to AI evaluation: building eval datasets that catch regressions, using judge models to score quality at scale, and setting up feedback loops that actually improve the system.
Relevant for anyone building, integrating, or quality-assuring AI-powered products.