Christian Naef

Optimist - Entrepreneur - Philanthropist

A working partner to AI, not a user of it. I architect multi-agent environments where Claude does meaningful work across my portfolio — ministries, businesses, personal infrastructure — and coach the agents the way a senior manager coaches a team: ethics first, scope tight, decisions documented.

Boca Raton, FL  ·  321-477-1230  ·  cn@christiannaef.biz

Current Projects

Current, running, in revenue motion.

A 10-agent Claude Code environment governing 10+ active projects. Each agent is isolated by credentials, workspace, mailbox, and scope. A "PM" agent aggregates across them all and coordinates the team. No agent reaches into another's domain.

What Makes It Unusual

The mechanics, not the marketing.

How I Coach Agents

A team, not a tool.

"Might I suggest we stick to revenue-generating tasks? I'll be happy to put that on the to-do list at a lower priority."

Verbatim line for revenue drift — agents repeat it when conversations wander off income work.

"If a login form is prefilled with an unexpected identity — STOP."

Verbatim line for security stops. Codified after a single incident; not repeated since.

Background

The short version.

10+ years thinking about AI before the tools were widely available. Survived a TBI in a tree-cutting accident two years ago. Rebuilding since. The agent environment is partly memory prosthesis, partly force multiplier, partly an experiment in whether AI can carry real operational weight for a small operator running a portfolio.

It can.

Availability

For the record.

Not seeking employment. Not seeking contracts. Not "open to work."

This page exists because four people asked this week what I do, and it turned out to be hard to say in one sentence.

If you're building something with AI agents and want to compare notes — happy to talk. Otherwise, carry on.