← Notes

10-21-2026

How I work with AI

My newest personal software is Pebble, a bespoke language learning app I built for my own learning. It transcribes Chinese podcasts, adds pinyin and English on demand, and exports vocab to Anki. Building it in Claude Code sharpened how I think about designing AI products, so here’s how I work with AI. The full Pebble story is in the case study.

AI-second, not AI-first

Pebble runs on AI, but I design it AI-second. This philosophy comes from Vitaly Friedman, who asks us to add “quiet AI” only where it removes friction or speeds up success. An AI-first mentality tends to turn teams into a feature factory of sparkle buttons, chatbots, and slop.

I reduced the problem to first principles through Jobs to be Done and the five whys instead of relying on uninspired, overused design patterns. Chatbots, for instance, are ill-fitting for audio transcription. So, I designed a familiar script-like interface, showing pinyin when you toggle it on and English on tap. With so many proven design patterns available, being a chatbot loyalist is a local maximum, not a global one.

Trust is the limiting factor. Numerous Nielsen Norman Group studies show that advertising AI features make people expect upsells, hallucinations, and credits that run out fast. That puts the burden on design. Our job is to help people reach a good result in fewer prompts, so they succeed before they hit a credit limit and the company isn’t paying for every retry.

How I build with Claude Code

I built Pebble end to end in Claude Code. I wanted to start learning from podcasts as soon as possible, and an MVP that covered the core jobs to be done (a non-negotiable) would deliver value right away. The last 20%, the taste layer, could wait for later versions. My setup is the usual Claude Code playbook:

  • Plan mode before big changes, so we agree on the approach before any code is written
  • A CLAUDE.md that works like a product spec with guardrails, establishing what Pebble must never do, and which actions need my sign-off
  • A design system in Claude Design that Claude checks for exact sizes and tokens before building UI
  • Skills for repeatable work, like commits and fixing failing tests

Prompting is a refinement journey that I try to optimize. I ask Claude to interview me before it starts, so it captures my vision and doesn’t waste tokens on guesses. I also use sliders to fine-tune UI details to take control over the taste layer.

AI can’t one-shot a design and probably never will, so I ask Claude to generate three visual directions. This way I can play with the brand direction, micro-interactions, and feel before committing to one—or combining the best parts of each—to refine.

Three visual directions for Pebble, Scholarly, Editorial and Wabi-sabi, combined into a fourth

Design agents

Taste is something you cultivate a sensitivity for through tacit knowledge. How might we leverage AI tools to reflect that in our work? After reading Claire Taylor’s essay, I started keeping a taste journal in a skill file and adopted a new agent:

  • Taste maker: gathers my recent saves from Substack, Instagram, and X, asks what they reveal about my taste, and turns the answers into heuristics for my design.md.

I still prefer to rely on my own knowledge of best practices and heuristics for design critiques, as well as user testing. Outsourcing that to an agent works for evaluating visual consistency across a system, but now that AI can generate design (even if it can't one-shot it), critical thinking, process, and authority is kind of the whole point of hiring a designer.

Try Pebble

The live demo runs on sample episodes and Luvvoice AI voice actors, but I run a local-first version where I upload my own audio, so I can translate and learn while listening instead of leaving the app and opening new tabs.

I’d love for you to try it. Email me at [email protected], and if you want to use it with your own audio, I’ll build it for public use.