I spend most of my week building AI products. Agents, pipelines, evals. I genuinely love this stuff.

But the project I keep coming back to has almost nothing to do with any of it.

For four years, I've been the design partner for Bicycle Health, the largest provider of virtual opioid use disorder treatment in the US. More than 40,000 people have come through their digital doors. For most patients, the website is the first point of contact. They arrive in one of the hardest moments of their lives, often carrying shame, often after a healthcare system that judged them. They're deciding whether they can trust anyone with the most vulnerable part of themselves.

The design work there isn't clever. It's warm instead of clinical. Plain language instead of medical jargon. Certified accessible, because someone in crisis might be on an old phone with shaking hands. Nothing is pushing anyone faster than they're ready to go. If the site feels cold or complicated, they close the tab, and closing the tab can cost someone their shot at recovery.

We talk a lot about what AI will let us build next. We talk much less about the people who aren't having a great time right now, and what design can do for them today.

Check it out

As a software engineer, this really resonates with me. We often focus on architecture, performance, AI capabilities, and shipping faster, but the real measure of a product is whether it helps people when they need it most. Thoughtful design, accessibility, clear language, and...