I build AI systems
that make businesses
money.

AI systems that do one of three things: bring in more customers, increase what each one is worth, or cut the hours your team spends on manual work. In practice that’s lead qualification and follow-up, onboarding and CRM automation, internal knowledge assistants, automated reporting, and connecting AI safely to internal tools.

It starts with an audit — I map how work actually moves through your business and rank what’s worth automating by hours saved and build cost. From there we scope one system with a measurable outcome, I build and deploy it, and you get the source code and documentation. Most clients then move to a monthly retainer so the system stays monitored, tuned and extended.

Audits run $180–600. Most builds land between $900 and $4,500 depending on how many sources and integrations are involved. Ongoing support and iteration runs $1,500–2,500 a month. You’ll get a fixed price before any work starts — no hourly surprises.

TypeScript and Python for the systems themselves, Claude and OpenAI for the AI layer, Trigger.dev for durable workflows that survive failures and retries, Postgres with pgvector for grounded retrieval, and n8n or Make where a visual tool genuinely fits. I integrate with the tools you already pay for rather than replacing them.

Credentials stay server-side and never reach the model. Access is scoped so a system can only reach the data it’s meant to. Everything can run on your own infrastructure if you need it to, and every decision the system makes is logged and auditable.

Book a call and bring one workflow that’s eating your team’s time. In 30 minutes you’ll know whether it’s worth automating, what it would take, and roughly what it would cost. You’ll get a written summary afterward either way.