What the work actually looks like.
Past engagements with people and teams. They drove, I guided, and they came away with working tools and workflows, and a way of working with AI they can keep going with on their own.
People inside companies making their function work better: replacing the spreadsheet that runs a process, or shipping what a client asked for. They often sit outside engineering and know the work best.
Working with a program management leader at a large tech company to replace the spreadsheet planning process their executives reviewed monthly, with a tool they built, deployed, and extended themselves.
Coaching an operations professional with no software background to build a client-requested feature into their company's production portal and navigate the review and release process that ships it safely.
Researchers turning what they know into working software and analysis: the science sets the questions and the standard for a right answer, and coding agents carry the work from question to result.
Working with a Stanford hematology fellow to analyze flow cytometry data with methods chosen by the science, then presenting the work at NYSDS 2026.
Six months with the analytics team at the Center for the Helping Professions, a nonprofit working in partnership with the University of Kentucky, building a language-model classification workflow their team now extends on its own.
People building their own fluency, from a first line of code with an agent to seasoned engineers sharpening how they build: real problems, their hands on the keyboard, and a way of working with AI that carries to the next project.
Coaching a professional image-retouching expert, from a first prototype to building and maintaining AI image tools used across their design organization.
Working alongside a classically trained CTO to fold coding agents into their real work: capturing a session as context, planning, implementing, and reviewing a PR together.
Two separate pieces of work with a senior engineer at a big tech company: an interview-plus-agent review that caught a costly blind spot, and codifying their git workflow into personal agent skills.
Mentoring a designer with no coding or language-model experience over many months, from fundamentals to building complex applications, including a personal agent they develop and operate on their own.
Stop experimenting with tools. Start solving problems. Every one of these stories started with a real one. Tell me a little about yours, or your team's, and we'll find a useful first project on a short call.