I spent years turning ambitious ideas into products by bringing teams together. AI has given me a way to build those ideas directly, from prototype to working system, and I’m hooked.
I use AI heavily as part of my toolchain. On my independent builds, I own the product decisions, architecture, review, iteration, and delivery. The case studies separate my contribution from the wider team’s work.
Accessibility · Public interest
Bunch: a context system for continuity across memory gaps
I built Bunch to meet a continuity need that the tools I had tried did not address: recovering working context across memory gaps. The source code and data model are public to inspect, and a no-sign-in demo uses fictional records. The engineering problem was preserving context so the right information surfaces at the moment it matters. The accessibility problem turned out to be the same problem in a different hat.
Bunch’s published data model: people have pictures, hosting history, and fronting history; a return can have a catch-up with saved notes, tasks, decisions, and conversation summaries. Hosting records responsibility; fronting records presence.
Builder · AI systems
A job-search cockpit where AI can draft but cannot invent
I built a private workspace to run my own job search: it finds leads, drafts tailored applications, and hands batches to a local MCP worker. The design problem was trust. An AI that writes applications will happily invent experience, so the model only chooses which of my reviewed résumé claims fit a role. The draft is assembled from those claims’ exact text, and nothing counts as submitted without a saved confirmation.
Turning AI adoption into measurable, repeatable practice
At ActiveCampaign, I led AI enablement and transformation across engineering, product, and leadership. I paired adoption goals and operating metrics with accessibility-first learning experiences that made practical experimentation possible.
Building internal tools and moving a blocked initiative forward
At Guaranteed Rate, I acted as product owner for a data-mining tool associated with $1.5B in locked loan volume. The work required turning complexity into priorities, risks, trade-offs, and a path through ambiguity.
I like the seam between engineering and product: make the smallest useful thing, learn from reality, then leave the system more legible than I found it.
Start small. Ship fast.
Build the smallest useful thing first, then learn from reality.
Make it legible.
Useful beats impressive. If people can’t understand it, they can’t use it.
Build for handoff.
Good systems should be maintainable, teachable, and bigger than one heroic person.
Build for people, not just problems.
I look for the thing keeping people from participating, then build a door through it: lower friction, widen access, create connection, and give people new ways to take part.
What happens if you bring me in
From fuzzy opportunity to an owned system.
01
Prototype
Turn an ambiguous opportunity into a working artifact people can react to.
02
Instrument
Define what success means and measure the behavior that matters instead of relying on vibes.
03
Operationalize
Build the boring-but-essential evaluation, documentation, and handoff around the useful thing.
04
Enable
Teach the pattern well enough that the team can keep moving without a permanent wizard in the basement.
I’m looking for hands-on AI work: take an ambiguous problem, build the first useful version, and keep going until other people can use and own it. I bring the product judgment, program leadership, and enablement experience to make that happen. I also take on focused consulting projects.
Nine Pull Requests to Connect One Account: A Bunch OAuth Failure Analysis
How connecting Bunch's OAuth-protected MCP server to ChatGPT failed nine different ways, what each failure showed about the client, and the security boundary that stayed fixed throughout.
I’ve spent my career moving between disciplines that are usually treated as separate. That turns out to be very useful in a text-first AI world. I’m happiest where product, engineering, communication, and a slightly unreasonable amount of curiosity overlap.
16+ years delivering customer-focused software solutions.AI transformation leadership, program management, agile coaching, and practical building.
Twenty years of published writing under several names.Novels, short fiction, poetry, essays, and the occasional live performance.
I care about tools that survive contact with actual humans.Accessibility, legibility, and adoption are product requirements, not garnish.
Unpaid work that ships.Accessibility software and nonprofit conference operations, because the through-line has always been building for people the tools ignore.
