I asked myself a new question. Not "what's going to break this if I keep using it." More like: what would break this if someone were trying to?

Steph PawlowskiAugust 24, 2026AI, accessibility, testing

When I Couldn’t Resolve a Bug in my Project

When I built my accessibility triage tool, I hit a bug that I couldn’t resolve despite throwing more and more time at it. I had to make a decision - do I ignore, or do I write up what is actually going on?

Steph PawlowskiAugust 18, 2026AI, trust

Building AI Tooling that Matters + Fun with Accessibility

The interesting design question wasn't "how do I get AI to find issues." It was "where does AI actually add something a deterministic tool can't, and where should I keep it out of the way."

Steph PawlowskiAugust 17, 2026AI, accessibility, axe-core, Claude, WCAG, Puppeteer

Teaching an AI to Ask Before It Acts

Ask an AI a question and it will answer. Usually right, sometimes wrong, but it answers. That's a different skill from handing an AI a task, some incomplete information, and a set of tools, and asking it to figure out what to do next.

Steph PawlowskiAugust 14, 2026AI, Cloudflare, Claude, API, promptfoo, Node.js, GPT 4.1

Can an AI Tell You "No," and Know Why

I wanted to know whether an LLM could actually manage IAM: not just approve the obvious cases, but know when to deny outright, and know when the honest answer is "I can't decide this, a human needs to look at it."

Steph PawlowskiAugust 13, 2026AI, Javascript, IAM, promptfoo, Node.js

Teaching an AI to Say "I Don't Know"

If you hand an AI your documents and ask it a question, will it give you the right answer?

Steph PawlowskiAugust 11, 2026AI, Cloudflare, RAG, Voyage AI, promptfoo, Node.js