Michael Pace Resume (PDF)

Creating AI-built tools for everyday people.

If I have an idea, I open Claude Code and start building it. With Claude and OpenAI's Codex I've built a client app that handles health information, tools for my hospital IT job, and custom development tools for the Unity engine. Along the way I built my own setup: agents working side by side, skills I wrote for them, and tests that check what they produce.

How I build with AI

Agents write most of the code. I decide what gets built, write the rules they follow, and review the work before it lands.

The pipeline

  1. Project setup

    Before any code, I write unique instructional files (.md) that agents read first: rules, project layout and tests to run.

  2. Code agent

    Claude Code asks clarifying questions first, then builds each feature in the real codebase, following those files.

  3. Checks

    The agent tests its own work and shows that the change does what was asked.

  4. My review

    I approve it or send it back. Nothing destructive runs without my sign-off.

Studio companion app

A two-sided app for a local Pilates and fitness business. Clients use it on their phone to fill in their health form, book visits, follow the home program their trainer set, and ask questions about classes and prices. Staff get a dashboard with each client's record, an AI summary of the health form, session notes, and messages from the studio's website. It goes live in November 2026.

Staff dashboard
Staff dashboard showing an AI summary of a client's health form. Two flags are listed, and the sentences they came from are highlighted in the form beside it.
The AI's summary sits beside the client's own form, with the sentences behind each flag highlighted. Every person and health detail on screen is made up.
Client app home screen: the next visit, a Book a visit button, and the home program with a progress bar.
Client app booking screen: day buttons, a class with a Book button and a class marked Booked.
Client app Ask the studio screen answering a question about class prices and naming the page the answer came from.
The staff dashboard on a phone, on its Website messages page: two messages waiting, the first from someone asking about beginner classes, with buttons to email, call or mark it as dealt with.
The client app: home, booking, and the Ask the studio assistant answering a price question from the studio's own content. Last, the staff side: messages sent through the studio's website. Every name and message is made up.

How it works

  • The assistant answers routine questions, with the source.

    Clients ask about classes, prices and hours. The assistant answers only from the studio's own published content and names the page the answer came from.

  • It knows when to hand over to a person.

    Health questions are declined, with an offer to pass the question to the client's trainer.

  • Website enquiries land where staff already look.

    Contact-form messages and newsletter sign-ups from the studio's website show up on one page for every trainer and the owner.

Private health information stays private

  • The AI never learns who the client is.

    It receives health answers with an age in place of the birth date and no name, and nothing at all unless the client has agreed. If a client withdraws that agreement, what the AI wrote about them is deleted.

  • Every look at a health record is written down.

    Health forms are encrypted. Reading one always leaves a record of who read it and when, including attempts that were refused.

  • Staff see only their own clients.

    The database enforces who can see what, so a mistake in the app can't expose someone else's records. 179 automated tests check it, including ones that sign in as the wrong person and confirm they are refused.

Bringing AI into my day job

Smaller tools I built between tickets to help with day-to-day tasks.

Device scanner

Scan report
A report titled Peripheral Scan, listing two devices with problems and six printers, one flagged for using a generic driver.
A scan report ready to attach to a support ticket. It comes from a test on my home PC, with the PC name replaced.
  • Disk Space Cleanup

    Low-storage tickets kept coming up, each with the same manual steps. This tool runs them in order, protects logged-in users and shared clinical accounts, and logs the space freed per item for the ticket notes. I use it at work.

    Command PromptThe Disk Space Cleanup menu in a command window: free space on C:, then eight numbered options from a space report to a full cleanup.
  • Driver Search & Install

    It scans a PC's devices, explains each problem in plain English, works through seven fixes while asking before each change, and writes a report for the ticket.

    Command PromptThe Driver Search and Install menu in a command window: nine numbered options, including scanning devices and printers, fixing a driver and mapping a printer.

Hospital Wayfinder

Hospitals are confusing to get around, and ours had no floor map that was easy to pull up. I built a tool that takes the partial floor maps from AeroScout and stitches them into searchable maps with directions. I used it daily in my first weeks while learning the buildings.

Hospital Wayfinder
A wayfinding tool showing a route from Room 1-104 on Floor 1 to Room 3-229 on Floor 3, with five written steps and a floor plan with the route drawn to an elevator.
A route across two floors, with the destination typed as a PC's name. This is the real tool running on a made-up building; the hospital's floor plans and naming scheme stay private.

What it does

No patient data involved.

  • Type a room, get a route.

    Enter a room number or a PC's name and it gives step-by-step directions across floors, including which elevator to take.

  • It reads the room numbers itself.

    The tool reads the labels off the drawings instead of someone typing them in, about 2,500 so far, and ignores drawing codes and measurements.

  • It says when it's estimating.

    If a room isn't on the map yet, it routes to the nearest numbered room and says so.

  • Nothing to install.

    It runs as a single file on locked-down hospital PCs. Every floor is mapped and labelled. Routes work where corridors have been traced, which is only part of the campus so far.

Off-the-clock development

Outside work I use AI to help me create games in the Unity engine, from timed game jam entries to a full Steam release.

store.steampowered.com
The Steam store page for Zombie Crawlers: a screenshot of the game's map screen, styled like an old desktop window with rooms and a locked door marked, beside the game's cover art, a short description, and a release date of Nov 13, 2026.
Zombie Crawlers on the Steam store, with a playtest open to players and release set for November 13, 2026. See it on Steam.

How it's built

  • CLI and MCP connect agents straight to the tools.

    Agents drive the open Unity editor through its command line (CLI), about 140 commands, so they place objects, run tests and take screenshots themselves instead of hand-editing files. Over MCP, the standard for plugging tools into AI agents, the code agent pulls designs straight from Claude Design.

Email me Resume (PDF) LinkedIn