Chance Kelch
Former Amazon, StockX, and Stripe exec.
Now building reliable AI systems—and writing about what works and what doesn't.
Hands-Off Workflow
TL;DR: 12 commits, 6,500 lines of code, 4 hours, merged cleanly — and it wasn't an accident. The agent's choices came from my twelve-persona synthetic leadership process that made autonomy predictable.
Vibe-Coded Software
TL;DR: AI-generated code demos beautifully and collapses under pressure. I went from 79% → 93.5% test coverage and found 11 production bugs hiding behind 'working' features. What looks 80% done is actually 20% complete.
I Deleted My Production Database at 2 AM
TL;DR: I built a GDPR-compliant account deletion endpoint with AI. It hit production database. Nuked user tokens. Webhooks collapsed to dead letter queue. Circuit breaker popped. Self-healing couldn't heal. 11pm in bed, trying to move fast. Broke everything instead.
You're Using AI Coding Tools Wrong
TL;DR: Most developers use AI like autocomplete. I tracked 19 days: 7,583 lines/day with 93.5% test coverage. The win isn't speed—it's comprehensive testing, continuous docs, and proactive monitoring baked in.
When AI Creates Documentation Faster Than You Can Clean It
TL;DR: AI generated 100+ docs in 2 weeks. Great for exploring ideas. Terrible for findability. The fix wasn't cleanup—it was 5-layer automation (gitignore, pre-commit hooks, CI, cleanup scripts, cursor rules) to prevent proliferation.
Context Management at 1M Tokens
TL;DR: The half-life of superintelligence is about 30 minutes. Claude can be mid-refactor, then start undoing its own work. I hit context limits constantly running multiple instances. Built a TEMP file system with cursor automation that preserves state when the AI forgets.
My 12-Person Leadership Team Lives in a Markdown File
TL;DR: I don't have a CTO, CFO, or Legal counsel. But I consult them before every major decision. Built a 12-persona framework that shows tradeoffs—then I make the call. Automated bureaucracy that works.