Now shippingForeman CT23:22:17 Dallas, TX Business systemsApplied AI I build the systems revenue and operations run on, and the AI inside them.
Teams buying AI keep hitting the same bottleneck: the CRM, billing, reporting, and operator
workflows underneath do not line up. I work inside the stack a business already runs, add
agents where they earn their place, and hand back a system with eval gates, human review,
and clear operator control. A managed IT provider’s monthly billing has run that way for
about 19 months.
CoHost AI Studio Stricter eval gate on CoHost transcripts
Throughline Retry-queue backoff in Throughline
focus business systems · internal tools · applied AI
based Dallas, TX · CTAug 2026
Two skill stacks that don’t often overlap.
AI teams often hire engineers who have never owned a CRM pipeline or a billing reconciliation. Operations teams often hire generalists who have never shipped an evaluated agent system into production.
I sit between those lanes. Ten-plus years owning the systems that move work from a new lead to a paid invoice is the base layer; internal tools, applied AI, eval harnesses, and human review are the newer layer on top.
That means practical delivery inside the business systems a team already runs, not a research project that sits apart from the work.
10+yrs
Owning production systems across customer data, billing, reporting, and operations.
202
Customer accounts where one audit caught a billing bug before the next invoices went out.
7
Systems with a public case study, with claims traced to code or clearly marked self-reported.
Selected systems
Things I’ve shipped. Each links to a case study. All7AI automation2Tools and operations3Billing automation1Revenue systems1 
Meter Shipped Billing automation PythonConnectWiseIntermedia ~19 mo in production billing a real MSP
202 accounts in one audit incident (self-reported)
Read the case study 
CoHost AI Studio In progress AI automation PythonTypeScripteval harnesshuman-in-the-loop 20+ pipeline steps
11 quality metrics
AI gated publish
Read the case study 
Throughline Shipped Revenue systems PythonPostgreSQLOAuth 2.0retry queues Read the case study 
Live TV production automation Shipped Live operations vMixPythonVB.NETstudio systems Read the case study 
EnrichCRM Shipped AI automation TypeScriptNext.jsGeminiOpenAI Read the case study 
Foreman Live AI tools 
Tether In progress Internal toolsNothing in that category yet. Try another.
You can open all seven without a login. Each uses a real server, synthetic sample data, and labels that tell you what it proves.
RevOps Software Factory Featured Applied AI · RevOps Recent work
Updated continuously Adapting Cloudflare’s $1 Review Factory for RevOpsAgent systems · RevOps architecture Cloudflare’s code-review factory, adapted to revenue data: coordinator, specialist fusion, risk-scaled compute, and the resilience work needed to make it usable as a demo. Read the article ~7 min read The Four-Method Connector Contract — and Knowing When to StopThroughline · Connector design A four-method connector contract that keeps six vendor integrations behind one engine-owned sync boundary, plus the restraint it took to keep the interface small. Read the article ~10 min read How I work
The layer between AI and day-to-day operations: customer data, billing, reporting, internal tools, eval gates, and the workflow logic operators actually depend on. Small surface, strong contracts, practical automation, and a clean handoff to the people who run the process after the engineering work ships. When a process is manual, fragile, or hard to trust; when the data crosses systems that disagree; or when an AI workflow needs a quality bar, a review layer, and an operational owner. Where I am not the right fit Pure ML research, ground-up infrastructure, Kubernetes platform work, or roles that also require me to own visual design. I will tell you when a role is a stretch rather than overstate the fit.