Journal
Notes from the workbench.
Long-form thinking on agentic AI tools, software engineering, Mozilla, business workflows, and the parts I'm still figuring out.
All writing
Browse the journal.
Prompting Matters: What 18 Months of LLM Code Generation Taught Me
A long, opinionated tour through the prompting strategies that actually move the needle when you use AI agents to reason about class-level code, and the ones that look smart on paper but quietly fail.
Mar 14, 20268 min
Bridging Test Plans at Firefox with a Small, Boring Pipeline
How we wired an agentic GPT-4 workflow into Firefox QA without rewriting the workflow. The boring parts mattered more than the model.
Nov 2, 20256 min
Five Months Inside Bugbug
An honest retro of my Outreachy internship at Mozilla, shipping accessibility-tag and spam-detection models into the Bugzilla pipeline.
Apr 8, 20245 min