Teams buying AI still hit the same bottleneck: CRM, billing, reporting, delivery, and operator workflow layers that do not line up cleanly. I work inside the stack a business already runs, map how the process actually works, add agents where they create real leverage, and ship the result back as a reliable system with evals, review gates, and clear operator control.
A lot of teams can find either an AI engineer who has never owned a CRM or billing workflow, or an operations generalist who has never shipped evaluated agent systems into production.
I sit between those lanes. Ten-plus years owning lead-to-cash, CRM, billing, and reporting systems is the base layer; applied AI, internal tools, evals, and human review are the newer layer on top.
That combination is a strong fit for Dallas-Fort Worth hiring right now: companies want practical AI delivery inside existing business systems, not research projects floating above them.
Nothing publishes until it clears the gate.
An automated post-production pipeline with AI-assisted gating before anything publishes.
One connector interface, every system in sync.
A multi-connector ETL platform syncing QuickBooks, Copper, Basecamp, and PandaDoc to PostgreSQL and Airtable behind a shared connector interface.
Every record accounted for on the way into one identity layer.
A PostgreSQL-staged pipeline that ingests Airtable records and resolves them into a deduplicated master-contact identity layer with reconciliation reporting.
Intermedia usage, billed straight into ConnectWise.
Full-stack billing automation syncing Intermedia usage data into ConnectWise agreements.
Read the case study
CSV in, enriched contacts out, at a fraction of the cost.
A contact-enrichment pipeline: a Brave + Gemini CLI and an OpenAI + Firecrawl web UI, with per-contact cost tracking.
Read the case study
Where scattered business data becomes client intelligence.
A Postgres-backed client-intelligence system that syncs Airtable records, normalizes identity fields, and surfaces a unified client view with source lineage.
Read the case study
Keeps your AI coding sessions alive and restarts the ones that hang.
A terminal session supervisor for AI coding assistants.
Read the case study
Run your dev ops from your phone.
A macOS daemon and CLI for mobile-first development ops.
Read the case studySix interactive proofs you can open and try — each runs on a real server-side backend. Synthetic sample data, honest labels, no login.
The four-method contract that turned 2,000-line integrations into 50-line entry points. The 40× is entry-point LOC only; API savings are doc-stated in the post.
Meter · Billing automationHow preview-before-sync, ghost-addition detection, and DB-level locking keep MSP billing reconciliation from duplicating or dropping charges.
The business-critical layer between AI and operations: CRM, billing, reporting, internal tools, agent retrieval quality, eval gates, observability, and the workflow logic operators actually depend on.
Small surface, strong contracts, practical automation, and a clean handoff to the operators who run the process after the engineering work ships.
When the problem is manual, fragile, or hard to trust; when the data crosses systems that disagree; or when an AI workflow needs a quality bar, review layer, and operational owner.
Pure ML research, ground-up infrastructure or Kubernetes platform work, or anything that requires me to also own visual design. I will tell you when something is a stretch rather than overstate the fit.
Always glad to compare notes with people building applied-AI workflows, internal tools, and the business systems they run on. Reach out any time.