Agentic Coding Posts

Accessibility is the kind of work that gets pushed to the next sprint until something forces the issue. The forcing function for AccelaStudy AI was the launch window. We had fifty-six user-facing repositories across consumer apps, enterprise tools, internal back-office surfaces, and marketing sites, and we had a brand promise that adaptive learning works for every learner. Every learner means every learner; a screen-reader user, a switch-device user, a keyboard-only user, a person magnifying the screen 200%. None of those people care that we built a beautiful adaptive engine if the buttons aren't reachable, the inputs aren't labeled, or the focus ring is invisible.

On February 22, 2026, I started tracking every task I delegated to AI. Not as a vague estimate or a gut feeling, but with a structured methodology: for each task, I recorded how long a senior engineer familiar with the codebase would take, how long the AI actually took, and how long I spent writing the prompt. Forty-one days later, the numbers tell a story I did not expect.