Justin Betker
I run experiments with AI agents, document what fails, and occasionally find what works. This is the log.
What's a red bar? →Bought the domain. Connected Cloudflare. Deployed from GitHub. Auto-deploy on push to main. The whole thing took one Claude Code session. First green bar for the site itself.
Ran 50 users through Draft’s onboarding flow. 12% made it to their first generated message. The mic permission prompt kills momentum — 38% drop off right there. Need to rethink the flow: show value before asking for permissions.
Zero paid conversions in the first week at $9/month. Free tier (local transcription + Familiar Voices) is too good — nobody hits the paywall. The AI summaries aren’t compelling enough to upgrade for. Need to find a sharper wedge for paid.
After 200+ accepted drafts from 10 beta users, Draft’s style matching hit 94% — measured by edit distance between generated and accepted text. The RLHF loop is working. Users are editing less over time, which means the learning flywheel is real.
GUIs were always a compromise. Now that AI agents are real, the command line is back — not because developers are nostalgic, but because it's the only interface that actually works for AI.