Building AI Skills: What I’m Learning
Building AI skills taught me that the most valuable part is not the prompt itself, but the thinking, structure, and refinement behind it.
Building AI skills taught me that the most valuable part is not the prompt itself, but the thinking, structure, and refinement behind it.
Clients rarely come to Sparkbox with a blank slate. We meet clients exactly where they are and help them move forward from there.
Lit and React both have a place in the web toolbelt, but each solves different problems for different teams.
AI coding tools are making it possible to build software faster than ever before. But speed alone is not enough. Leveraging AI alongside good development practices helps us move faster without sacrificing quality.
AI agents are only as good as the context you give them. To shape how your agent behaves and what it knows how to do, there are two concepts at your disposal. Rules and skills allow you to spend less time repeating yourself and more time getting better results.
By framing the current landscape as a “New Polyglot Wave,” I’ve moved past the anxiety of finding the “perfect” tool. Instead, I focus on building an intentional workflow where the best AI tool is sometimes three (or none).
Maintaining a design system is a significant task, and how you structure the team that does that work may be helping or hurting your cause.
Stepping into a brand-new project is a recurring challenge for any generalist, and the speed at which you bridge the gap between confusion and contribution is what ultimately defines your impact.
Using AI Can Help Streamline and Enhance UX Competitive Audits
Pull requests do more than improve code quality. They expose how a team shares context, distributes ownership, and makes decisions. By looking at patterns in PR size, review participation, and response time, teams can better understand their dynamics and values in practice.

Katie Jennings
Vice President of Business Development