Art
Tiongson
Operations Builder · Directs Agentic AI |
I direct AI agents to build production software. My domain is operations and accounting: I own the problem end to end, requirements, architecture, and source-verified validation, while agents write the implementation under my standards.
How I
Got Here
I ran $65 million in store operations before I ever wrote a line of code. That's why I build differently, and why I now direct AI agents to ship the systems I used to wish for.
Before moving into product accounting, I led store operations at a major national retailer, managing a $65M book of business, leading cross-functional teams, redesigning operational workflows, training staff on new systems, and owning the P&L outcomes.
When I moved into product accounting, I found myself working inside Microsoft Dynamics NAV, running monthly close processes and managing inventory reconciliation. Within my first month, I looked at a reconciliation workflow that consumed 2-3 days every cycle and I decided to fix it.
I fixed it. I directed AI to build an automated Power Query pipeline pulling live data through ODBC connections directly from our ERP database. What took days now takes one click. The real lesson was not that AI could write code for me. It was that I could direct it to build real systems, and that the constraint was my judgment about what to build, not the typing.
So I escalated the same skill: from automating one report, to directing agentic coding workflows in Claude Code, to running multiple AI agents in parallel under my direction and building the custom tooling (MCP servers) that extends what they can do. The output: Jarvis, my private, always-on AI assistant with a governed agent runtime, full-duplex voice, two-way iMessage, and a human-gated self-modification loop; an open-source Excel MCP server that gives agents token-bounded access to spreadsheets; Ombri and ArtFitness on iOS; Music Tool on iPad; the five internal systems in Work Systems below, from a daily-driver inventory diagnostic app to a six-tool team reports portal; and this site. I directed agents to build all of it.
I don't position myself as a traditional developer. I'm an operations builder: I see where processes break down, and I have the judgment and the tooling to fix them. AI writes most of the code; I own the problem, the architecture, and whether the result is actually correct.
How I Work
I don't write the code, and I never have. I direct AI agents to build it. My job is the part the agents can't do: owning the problem, setting the architecture, holding the standards, and verifying the result against the source.
Impact
What I Work With
Things I've Built
Jarvis
A self-hosted AI assistant platform with the Claude API as its reasoning core. Full-duplex voice, two-way iMessage, and smart-home control, with persistent memory and a permission layer that allow-lists and audits every tool call.
ArtFitness
A native iOS workout app with an AI coaching engine that gives real-time, in-workout feedback informed by your training history. A REST API exposes workout data to other tools, and response caching keeps per-user inference cost in check.
Excel MCP Server
An open-source MCP server that lets an AI agent read and manipulate Excel workbooks directly, with token guardrails that keep large-file operations inside the model's context window.
Built on the Job
Internal systems I directed AI agents to build for the accounting and operations team I work in. Employer, data, and internal names are withheld.
Personal Inventory Diagnostic Tool
My daily-driver desktop app for running the monthly inventory close. It pulls live ERP data over ODBC into a cached parallel refresh, then runs an anomaly engine that flags the posting errors the ERP drops silently: assemble-to-order sales with no assembly output, negative on-hand, stale stock, activity in the wrong site. A reconciliation workspace with a month-end snapshot lock replaced the stack of ad-hoc workbooks the close used to start from.
Billing System Rebuild
A billing portal built on a low-code platform by one power user, with no source control and no written spec for its core logic. I reverse-engineered the billing-line generation from the database outward, documented the derived rules, and directed the rebuild as an ASP.NET Core app, with writes gated off until the new engine back-tests clean against 166,000 historical billing lines.
Company Brain
Institutional knowledge lived in people's heads and thousands of old files. I directed fleets of parallel AI agents to mine hundreds of working sessions and a 92,000-document archive into a 12-chapter, source-traced knowledge base, every fact carrying a trust flag and a citation. My agents now retrieve verified facts instead of re-deriving them every session, and the standing context they load dropped by more than half.
Team Reports Portal
A team-facing web portal I stood up on an internal Windows server: one landing page, six tools the team uses every week — job cost reports, fiscal-period sales analysis, a billing portal, a company P&L, a daily transfer worklist, and a live ERP inventory lookup. Each tool is its own app reading live ERP data behind a shared front door. One monthly deliverable it replaced, a 2,000-plus-row manual pull, now ties out cell-for-cell against the hand-built original.
WIP Valuation Engine
Monthly work-in-progress valuation for a live growing operation, covering 1 to 1.6 million individual plants across two sites. A validated as-of SQL model over the production-tracking system, a four-layer per-plant cost stack, and unit-grain guards that catch trays booked as plants. Fixing one grain error cut variance between two independent quantity methods by roughly two-thirds.
Old Projects
Ombri
Finance by the hour: a personal finance iOS app with a time-of-day aesthetic. Morning, afternoon, sunset, and night themes shift the interface as the day moves. Currently in beta.
Music Tool
An iPad reference tool for guitar, ukulele, and bass. Chord library with color-coded voicings rendered on a live fretboard, scale visualization, chromatic tuner with autocorrelation pitch detection, and a songs workspace with chord diagrams.
Let's Connect
I'm open to roles where one person owns real surface area where software meets an industry vertical, the kind of work where I turn operational problems into shipped software.
