How I got here.
I started on factory floors. At Alpha Measurement I pulled usage history out of the warehouse ERP, ranked every part by how often it moved, and put the fastest movers closer to the pick face. Average pick time dropped 25%. At Tesla I built material flow models and warehouse layouts across three production shops, and identified millions in savings in dock allocation and storage. At Boeing I keep an eight-person engineering program on schedule as Scrum Master, and built the data systems that cut executive reporting time by two thirds.
That is the whole pattern. Find the thing being done by hand, build what replaces it, measure what changed. Industrial engineering is how I think about it: inputs, constraints, outcomes. It is also why the systems I build are ones I trust to run on their own.
Over four months in 2026 I spent nights and weekends building Soltreya, a quality platform for regulated manufacturers, on a multi-agent framework I wrote from scratch. It was a project rather than a company, and I am no longer actively building it. It is the best proof I have that I can take a system from nothing to production on my own.
Where I've worked
- Coordinate systems integration across 3 partner companies and 6 government organizations, and run the Agile process as Scrum Master for an 8-person engineering team.
- Built the team's authoritative data source, the single record of status, dates, and owners for 48 integration activities. Cut executive briefing prep 67% and fed automated KPI dashboards.
- Built a Qlik Sense dashboard giving chief engineers a live view of integration risk, with 50+ findings tracked to resolution. One of 3 finalists in a business-unit-wide innovation competition for it, demoed live to the executives judging.
- Defined the compliance assessment process across both sides of the interface for 336+ requirements, standardizing how each side verifies, documents, and reports.
- Identified $3.4M in dock-allocation savings and cut storage 66%; redesigned delivery routes for $4M/yr additional OPEX reduction, freeing 16,000 sq ft.
- Built material-flow models for 3 shops (250+ parts) in Revit and AutoCAD; raised lineside part buy-off rate from 54% to 95% through validation meetings with four engineering disciplines.
- Cut average pick time 25%: pulled historical usage from ALERE ERP, ran an ABC analysis to rank parts by running volume, and reslotted the fastest movers closer to the pick face.
- Created the processes and work instructions that scaled production to 5,000 units a month, and established 5S lean workspaces across shipping and the raw material warehouse.
- Returned as the Industrial Engineering intern after a first summer as Special Projects intern, running the warehouse's ERP inventory transactions and moving parts out to the production shops. Doing the job by hand first is what showed me what to optimize.
- Automated a hospital therapy department's daily productivity reporting, cutting supervisor reporting time 66% (90 to 30 minutes) and removing manual calculation errors.
- Architected the WAT framework (Workflows, Agents, Tools) so multi-step AI runs unattended without compounding errors: I scope Claude to the judgment calls and keep execution in deterministic Python I wrote.
- Ran it in production: ~4,000 scheduled and event-driven runs a month on Trigger.dev, a Claude orchestrator routing to 7 specialist agents, 40+ Python tools, and 17 background jobs.
- Built the product (Next.js, Supabase, Stripe) to a 100 Lighthouse score with zero accessibility violations, behind a four-gate security model (rate limiting, auth, tenant isolation, cost caps).
What I've built
Soltreya: AI quality platform
Soltreya helps regulated manufacturers handle corrective actions: the root-cause and paperwork work quality engineers otherwise spend weeks on per finding. It finds and scores target factories, drafts outreach in my voice for me to approve, runs the Quality Hub product, and keeps itself running across 17 background jobs behind a four-gate security model. I built the whole thing myself, for manufacturers working under standards like IATF 16949 and ISO 9001. It is pre-revenue, and I stopped active development in June 2026.
The WAT framework
Workflows, Agents, Tools. The reliability pattern under everything: probabilistic AI handles reasoning while deterministic code handles execution, so 90%-accurate steps never compound into failure.
40+ Python tools
40+ Python tools and 17 TypeScript background jobs for sourcing, research, reporting, and outreach. They run on a schedule or fire from Telegram, email, and cron, and connect to 10+ external APIs.
bellwether
Open archive of developer-infrastructure pricing. A TypeScript pipeline that fetches public pricing pages daily, deduplicates the archive, and publishes a citable board. Runs on a homelab for under a dollar a month. View the repo
What I work with
AI & Automation
Languages
Web & Infra
Systems & Process
Modeling & BI
Domain
Foundation
Let's talk.
Questions about the WAT framework, Soltreya, or anything else on this page? Reach out. I read everything that lands in my inbox.