I'm always the first to try new tools in my environment. I like automating repetitive work, finding ways to speed things up, and experimenting with whatever I'm learning. Right now I'm helping my team move toward AI-native engineering. I share workflows that actually save time and help colleagues set up agentic coding environments with Claude
Claude Code is my main dev environment now. I've built a harness workflow on top of it that lets me prototype faster, and an automated testing framework that catches issues before they become problems. But the real win was creating a personal knowledge base to track tasks, progress, and what I actually learn from each project. It's become the connective tissue between how I code and how I think about what I'm building.
Part 1 of an agentic-coding measurement series. I tried to make my AI coding agent cheaper. A tool promised 71× savings. I measured roughly zero — then caught myself doing the same thing. I run AI agents on real codebases every day, and the expensive part is the searching. The agent reading file after file to find what matters. So when graphify, a tool that turns your codebase into a queryable graph, advertised it could cut that cost by 71×, I was instantly interested. 71 times is the kind of number that makes you install something without reconsidering. But I decided to take the long way
At Goover, I build AI-agent products for a personalized-report SaaS serving 150K+ accounts. I shipped amplee, a multi-tenant AI newsletter with an agentic chat copilot that landed a paying pilot.
I built Ralph, a custom autonomous-coding framework in Claude Code that cut MVP time from two weeks to three days and shipped 23 specs end-to-end. I own Goover's core AI report pipeline, where I dropped the failure rate from 10% to under 1%. Also manage our company-wide transactional notification service.
From 2019 to 2020, I was an Embedded Statistics Tutor at Laney College in Oakland. The program was brand new—they assigned tutors directly into classes so we could learn the material while helping students. I was one of the first in it.
My week looked like this: 6 hours in lectures, 2 hours of office hours, plus a 30-minute check-in with the instructor each week. I'd catch students during class, in drop-in sessions, track their progress, and work with the instructor to build learning plans when someone was struggling.
That semester, the pass rate jumped 16.7%. Small program, real impact.
Started as a volunteer math tutor at Laney College in 2018, helping students work through Algebra and Calculus in the math lab. The work was straightforward—meet students where they were, break down the concepts, answer the same question five different ways until it clicked. Eventually the college hired me officially, which felt like validation that the approach was working.
