Thoughts & Learnings
Notes from my own projects, mostly on testing AI agents and automating real work.
-
Testing AI
How to test an AI agent before it goes live (a test manager's checklist)
Write down what good looks like, count what you can count, then test the ways agents fail. The checklist I run on my own AI agents before anyone relies on them. -
Test automation
Playwright MCP in VS Code lets an AI agent drive your browser tests
How Playwright MCP lets an AI agent open a real browser, how to add it to VS Code and Claude Code, and how to turn one session into a test you keep and run in CI. -
AI agents
What is an AI agent, and how is it different from a chatbot or a workflow?
An agent is a model that picks its own next step towards a goal, inside limits someone set. How that differs from a chatbot and a workflow, with real examples. -
Testing
Will AI replace testers? What QA work is left, from 18 years in testing
AI is taking over test drafting and repetitive scripting. Deciding what good means, testing systems that answer differently each time and owning release risk are growing. -
Automation
What can AI automate in a small business? Start with one job
The jobs worth automating first, the ones to leave alone, and how to pick, build, test and hand over one automation before you start a second.