Featured Episode
Future of Testing | Debbie O'Brien on Playwright, MCP, and AI-Driven Testing
alexusadays
Listen Now
Debbie O'Brien
Developer Educator focused on Playwright, testing & AI agents
Recent Videos
Featured Podcast
Recent Podcasts
Signals: DevTalk with Michael Dowden
From Automation to Delegation: Learning to Work with AI Agents
In this episode, Michael Dowden sits down with Debbie O'Brien to discuss how AI agents and automation apply to both daily personal tasks and software development, from shopping and scheduling to automated testing, bug hunting, and development workflows. They explore what it takes to make this kind of automation work: breaking down complex problems into smaller tasks, providing agents with the right context, verifying their output, managing cost, and gradually building trust. Rather than replacing developers, agents shift their role toward coordination, delegation, and review. The key challenge is no longer simply knowing how to use AI, but learning how to structure work so that multiple agents can reliably contribute to it. The conversation also considers the boundaries of delegation, from financial and security risks to unreliable information and poorly integrated services. The central message is: start small, experiment with low-risk tasks, learn what agents can and can't do, and increase their autonomy as they earn your trust.
.NET Rocks
The Role of AI in Testing with Debbie O'Brien
How has testing changed in the era of AI? Carl and Richard talk to Debbie O'Brien about using LLMs to help build and validate tests, drawing on her work at Zephyr Cloud. Debbie talks about using Playwright to validate application workflows and generate documentation. This leads to a discussion about documentation being more important than ever, since LLMs will actually read it! Maintaining quality is a challenge with LLM-generated code and tests, so there's always a role for a critical eye in the process.
Recent Blog Posts
Get your site agent-ready
How to give AI agents a short map of your site, a full index, and clean markdown copies of your posts, and why that helps even if the big crawlers do not use the file yet.
Build an Offline AI Study App with Local Models (Liquid AI LFM3-1.7B)
I ran Liquid AI's LFM3-1.7B in the browser with WebGPU and built Grading Buddy, an offline study app that answers only from notes I've checked.
One Tool Call Instead of Four Pages: Adding WebMCP to My Site
AI agents that open debbie.codes in a browser can now use tools on the page to find my videos, posts, podcasts and courses, instead of reading whole pages and guessing.
DevRel Didn't Die, Its Audience Changed
Most evenings I put my agents to the test. I'm literally taking products I'm curious about and building something with them. This is how I learn and experiment with a new product.
My Hire Me Page Can Talk: How I Built and Tested a Voice Agent
My Hire me page can talk. Recruiters can ask it about my work by voice or text. Here's how I built it with my Grok Bot and ElevenLabs in one morning, and how I tested it.
Grok Bot Uploads My YouTube Videos For Me (Beginner Walkthrough)
Grok Bot can use your own computer too. I asked it by voice to find a video on my laptop, fix the audio and hand it to my other bots to get it ready for YouTube, with nothing going public until I say yes.