Work with me
I help teams turn AI tools into workflows they can actually run. I'm an operator-builder. I direct AI to do the work and own the judgment that decides whether it holds.
I run a one-person software shop where the building gets done by AI. I decide what we make, check the work, and fix what goes wrong. I learned how by building a whole system that way myself. Now I bring that same approach to other teams, with the safeguards that keep it dependable when no one is watching.
I turn AI tools into reliable operating workflows.
Most teams already have the models. What they're missing is the part that makes the models safe to lean on: where a human signs off, what gets logged, what happens when a step fails at the wrong moment. That is the work I do. I come in, map how the work actually happens today, and build a path to AI that holds up when real people depend on it.
The engagement is measured by outcomes. You get a workflow your team can run after I leave, and a clear record of what it does and where it stops.
The most practical starting points are lead follow-up, document and inbox routing, private knowledge-base setup, and small dashboards that make the workflow visible.
Five moves, in order.
However we start, the work runs the same five moves.
- 01 Current-state discovery. I learn your tools, inboxes, folders, handoffs, approvals, and real pain points before I recommend anything. No plan survives contact with how the work actually gets done, so I start there.
- 02 Low-risk pilots. I test the new workflow in a contained spot, on data that does not matter yet, with the access dialled down and a clear bar for what counts as working. If it fails, it fails small.
- 03 Autonomy boundaries. I draw the line between what the AI may do on its own and what waits for a person. Most failures I've seen come from that line being fuzzy. I make it sharp.
- 04 Human approval gates. I put a person at every point where a wrong move would cost you something. The gate is explicit, the approver knows it is theirs, and nothing scales past it until it earns the room.
- 05 Failure-mode review. Before anything grows, I go looking for the ways it breaks: stale context, claims with nothing behind them, actions that should never have fired, recovery paths that do not recover. I'd rather find those than have your users find them.
Three shapes, lowest risk first.
- 01 Workflow audit. A focused read of how your work actually happens and where AI can safely carry load. You walk away with a current-state map, risk notes, and a fixed recommendation for what to build first.
- 02 Controlled pilot build. We build one small workflow on sample or approved data, with access kept narrow. You walk away with a working piece, a runbook, and a straight verdict on whether it earned the right to grow.
- 03 Monthly workflow support. Once a workflow is live, I stay close enough to tune prompts, fix small breaks, review the numbers, and help decide the next practical step.
The fastest way in is one honest paragraph about the workflow that is annoying you. A plain note works best.
Broadcast-grade reliability, applied to AI.
The discipline comes from live broadcast control rooms, where one path going dark at the wrong second means a lot of people see the dark. Years in that chair teach signal flow, redundancy, calm escalation, and proof saved before anything goes wide. AI needs exactly that hand on it. Access to a model is the easy part. The hard part is knowing what happens when it is wrong, who catches it, and how fast they recover. That is the standard every workflow I hand over is built to.
I built the thing I am describing.
I run a private, voice-first AI system on hardware I own. One person, no team, built over roughly 150 hours a month since the start of 2025, in the hours that were not the day job or being a dad.
It carries enough continuity that work can keep moving across days and projects instead of starting cold every time I open a new window. I talk to it about what I am doing, and it keeps the relevant context close enough to work from.
I built it by voice, through AirPods, talking to a machine at home while I drove. That detail matters, because it is the test. A real workflow has to run while you are doing something else, away from the desk. This one does, which is the whole point.
For a serious conversation I'll walk you through a clean architecture overview or a controlled demo. What matters is the track record behind it: I've already done the hard version of the work I'm offering to do with you.
Where I am most useful.
Workflow audits
A clear map of one workflow, where it leaks, what AI should and should not touch, and the safest first build.
Controlled pilot builds
Small human-in-the-loop systems for lead follow-up, document routing, private knowledge bases, and dashboard visibility.
Monthly support
Tuning, small fixes, KPI review, and practical next-step decisions once a workflow is live.
How I work, plainly.
I direct AI workers and review what they produce, the same way I direct a control room. That is the job, and it's how the system I run got built. I'm self-taught, and I'll be straight with you on the first call about where my strengths lie and what fits.
Where I'm strongest is the operator's view: seeing how the whole thing has to fit together, where it will fail under pressure, and what to put in place so it holds. If that's the help you need, we will work well together.
Start a conversation.
If you're turning AI tools into something your team relies on, I'm glad to hear about it. Tell me what you're running, where it's rough, and what you wish it did. Plain is fine. I read it myself.
The fastest way in is one honest paragraph about your situation. A plain note works best.