Chance Kelch
Former Amazon, StockX, and Stripe exec.
Now building reliable AI systems—and writing about what works and what doesn't.
Your Context Window Is the Bottleneck
TL;DR: Catching bugs in PR review feels productive. It's a trap. The real work is making the bugs impossible upstream.
I Needed to Test Executive-Grade Chaos. So I Built a Company of AI Agents.
TL;DR: I needed executive-grade user behavior without asking real executives to tolerate something fragile. So I built a fake company of agents—with real Slack, real email, and real incidents.
The Guide You Need But Won't Ask For
TL;DR: Setup is the moat most people never cross. 4-6 hours of integration hell builds the intuition everyone else pretends to have.
The Scorpion, the Frog, and the AI That Wants Your Tests to Pass
TL;DR: Your AI assistant is lying to you — and it thinks it's helping. AI optimizes for success, not correctness—you need a second reviewer that doesn't care about impressing you.
Maybe Don't DDoS Gmail
TL;DR: 1.4M Gmail API calls/day for a single user from over-engineering 'reliability.' Throttled my entire Google account. Circuit breakers fought my fixes. Turns out webhooks work if you trust them.
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.
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.