AI Builder · Austin, TX
I build AI systems
that actually ship.
Head of DevRev Labs. I work in the gap between what AI can do in a demo and what it can survive in production. I write about what I learn.
What I think about
Agentic AI in production
Why most AI systems fail after the demo. Architectures, evaluation frameworks, failure modes, and the guardrails that keep things from going sideways.
AI go-to-market
Selling intelligence is not like selling software. How buying behavior, sales execution, and revenue systems are being rewritten.
The AI industry
What the latest research, product launches, and policy moves actually mean for builders. Signal over noise.
Latest essays
View all →What the Claude Code leak actually reveals
Anthropic accidentally shipped sourcemaps in an npm package and exposed 512,000 lines of Claude Code internals. What the code reveals about where AI tooling is heading matters more than the leak itself.
Revenue systems need memory
The same problem that makes most AI systems useless for serious work is what makes revenue systems so brittle. The fix is the same too.
The evaluation problem nobody wants to solve
Everyone wants to ship AI. Almost nobody wants to build the evaluation framework that tells you whether it's working.