AI product and full-stack engineer
I'm Rebecca, an Oregon-based engineer with 14 years of experience turning ambiguous ideas into dependable products. My work spans agent architecture, context and retrieval, full-stack product experiences, evaluation, observability, and developer platforms.
How I got here
I've spent 14 years building software products from the interface down through the systems behind them. Earlier in my career, that meant frontend architecture, design systems, developer tooling, and shared platforms used across large engineering organizations.
As AI became part of the products I was building, my focus shifted to a harder question: how do you make systems built on probabilistic models behave like dependable software?
Today I work at that boundary, designing agent architecture, context management, retrieval, evaluations, state machines, observability, and the product experiences around them.
An AI-assisted workflow that helps users define, test, and refine Sudowrite plugins. Increased total monthly plugin creation by over 260% relative to monthly creation levels across the previous year.
A map-centered research agent that connects public permit, planning, property, and geographic data to make neighborhood development progress easier to understand.
A local-first AI translation tool for i18n files. Translation across 200 languages runs on-device, while an optional tone transformer helps teams match their brand voice.
Product, platform, and agent architecture for reliable systems teams can extend with confidence.
Production agents built for reliable, measurable behavior.
Customer needs translated into polished products from discovery through iteration.
Shared foundations for reliable delivery and independent teams.
Designing a resumable streaming protocol for flaky connections, mobile backgrounding, and everything else that interrupts a long-running generation.
Learn how explicit intent state, deterministic transitions, XState, and intent-aware context help AI agents adapt when user goals and constraints change.
Use Linear Temporal Logic, XState, and TypeScript to turn AI agent workflows into testable safety, liveness, and execution-trace guarantees.
How to use dotenvx to encrypt .env files and commit them safely to git. Set up DOTENV_PRIVATE_KEY_CI for GitHub Actions and keep secrets safe from AI coding agents.
Here are the things I've been excited about lately.
