Founders, CTOs, and product leaders who need AI in production, not another demo. US, Canada, and EU clients.

Do you take on small projects?

Yes. The $1,000 audit is the fastest way in. Larger engagements run as six-week sprints.

What stacks do you ship in?

Claude and OpenAI on the model side. n8n, MCP, Postgres with RLS, TypeScript, TanStack Start, Supabase, and Lovable on the platform side.

Do you offer ongoing support?

Yes. Retainers cover observability, evals, model upgrades, and incident response after launch.

Book the $1,000 AI Production Readiness Audit. Within 48 hours you get a go/no-go and a ranked plan.

What is a custom AI agent?

A program that uses an LLM to plan, call tools, and act on real systems with guardrails, retries, and observability. Not a chatbot.

Which models do you use?

Claude (Anthropic) as default. OpenAI when tool-use or function quality demands it. Local or open-weight models on request.

How do you keep agents from going off the rails?

Evals before launch, guardrails at tool boundaries, Postgres RLS for data access, full logging, and kill switches. Production AI runs on receipts.

How do permissions work?

Agents act as scoped service accounts. Sensitive actions require human approval. Row Level Security in the database enforces who can read or write what.

Can you integrate with my existing stack?

Yes. MCP for tool exposure, REST or GraphQL when needed, and webhooks both directions. I do not require you to migrate.

Services

Production AI work. Shipped, owned, measured.

Three ways to work together. Each one ends with a system your team runs on Monday.

Audit first. Build second. Operate third. No slideware, no lock-in.

Start with the $1,000 audit See work

02 / Engagements

Pick the smallest move that unblocks you.

AI Automation Consultant

Map the workflows worth automating, ship the first one, hand it over. See /services/ai-automation-consultant.

Custom AI Agent Development

Single-agent or multi-agent systems with evals, observability, and permissions baked in. See /services/custom-ai-agents.

n8n Automation Builds

250+ production n8n automations under my belt. Webhooks, queues, retries, and human-in-the-loop. See /services/n8n-automation.

Claude Pilot Health Check

$1,000 audit. 90 minutes live. 48 hours to a go/no-go decision and a ranked action plan. See /audit.

03 / How we work

One operator. No agency markup.

I run engagements directly. You get the engineer who designs the system, writes the code, sets up observability, and trains your team. No account manager, no handoff, no surprises in week three.

04 / Geography

US first. Canada and EU welcome.

Most clients are US-based founders and operators. I work async with overlap windows for Canada and EU teams. Pricing in USD.

FAQ

Common questions.

Who is this for?: Founders, CTOs, and product leaders who need AI in production, not another demo. US, Canada, and EU clients.
Do you take on small projects?: Yes. The $1,000 audit is the fastest way in. Larger engagements run as six-week sprints.
What stacks do you ship in?: Claude and OpenAI on the model side. n8n, MCP, Postgres with RLS, TypeScript, TanStack Start, Supabase, and Lovable on the platform side.
Do you offer ongoing support?: Yes. Retainers cover observability, evals, model upgrades, and incident response after launch.
How do we start?: Book the $1,000 AI Production Readiness Audit. Within 48 hours you get a go/no-go and a ranked plan.

Not sure which service fits? Start with the audit.

The $1,000 AI Production Readiness Audit ends with a clear recommendation. If a larger engagement makes sense, the audit fee credits toward it.

Start with the $1,000 auditSecure checkout via Stripe