Break the Build

Sign in Subscribe

AI

How to use AI in real-world testing: from GPT-based test case generation to autonomous test agents and intelligent CI triage.

From Power Plants to Chatbots: How AI Really Works

From Power Plants to Chatbots: How AI Really Works

When you ask an AI a question; whether it’s ChatGPT, Claude, or something running on your phone; it feels like magic. But under the hood, there’s nothing magical about it. It’s an enormous industrial stack, stretching from giant warehouses full of computers all the way down to

The New QA Team: Evolving Roles in an AI-Powered Future

The New QA Team: Evolving Roles in an AI-Powered Future

The QA team you knew is no more. The new quality organization isn’t a team; it’s an intelligence function, woven throughout the software lifecycle. And in this next era, our roles are shifting as dramatically as the tools we use. Gone are the days when success meant writing

Why AI Won’t Replace QA Teams - and Why You Still Need Humans

Why AI Won’t Replace QA Teams - and Why You Still Need Humans

Every week I see a version of the same hot take on LinkedIn: “We don’t need QA anymore. We’ll just use AI.” - some CTO It’s a tempting idea. AI is everywhere, reshaping software development and automating tasks we once thought untouchable. If AI can generate code,

Building an AI Oracle to Cover Enterprise AI Agents

Building an AI Oracle to Cover Enterprise AI Agents

If you’ve ever tried to scale test coverage for an AI agent, you’ve probably hit the same wall most teams do: running the tests is easy; evaluating them is the hard part. Modern infrastructure can spin up tens of thousands of scenarios overnight. But knowing whether those 50,

Scaling AI Agent Testing from 200 Runs to 50,000: Building the Oracle You Can Trust

Scaling AI Agent Testing from 200 Runs to 50,000: Building the Oracle You Can Trust

Most AI teams run a few dozen, maybe a few hundred, tests on their agent and declare it “working.” But reality kicks in when you need to prove reliability at tens of thousands of runs. That’s when your 100 clean passes stop being evidence and start being a liability.

Icarus: Build Your Own AI QA Test Agent

Icarus: Build Your Own AI QA Test Agent

Most test engineers know the pain of keeping automation in sync with a fast-moving product. Locators change, flows shift, features evolve; and suddenly your test suite is brittle. That’s where Icarus comes in. Icarus is an AI-powered test agent I built that converts annotated screenshots → structured test cases using

The CTO Playbook: A 6-Month Roadmap for Implementing AI in QA

The CTO Playbook: A 6-Month Roadmap for Implementing AI in QA

Quality has always been the bottleneck of delivery. You can scale engineering, spin up cloud environments, and automate CI/CD; but QA is the last defense between your customers and production. Artificial Intelligence changes that equation. Not by replacing testers, but by expanding their reach. With the right plan, you