Essays and demonstrations on custom AI systems, accessibility engineering, agentic workflows, and the procedures that make output reviewable.
Showing all 6 writing entries.
AI agents are now participating in accessibility work. The question is whether we've made our practice available to them. POUR — perceivable, operable, understandable, robust — wasn't just for users.
The accessibility community has been solving AI alignment problems for decades. POUR principles are alignment primitives. The patterns that make content work for assistive technology are the same patterns that make AI systems trustworthy.
Context, Model, Prompt, and Tools—the four elements of every agentic system. Tools are where trust lives.
The practice of building AI systems that extend human capability without hiding their reasoning—for domains where trust isn't a feeling, it's documentation.
Accessibility isn't about compliance—it's about translating between fundamentally different ways of knowing. AI changes what's possible.
Technology should amplify human capability, not constrain it. A manifesto for enablement engineering.
No writing matches those filters.
Subscribe to the RSS feed for new writing, or use the resource library for definitions, prompts, templates, and reference assets that support the essays.