I run business functions using AI agents as the execution layer.
Not an engineer. Not a generalist. An operator who understands both
how a business works and how to make agents run it.
Most companies are about to face the same problem: they need to redesign their workflows for agents, not for people. But they don't have anyone who understands both the business function and the AI layer well enough to make that transition work.
The agent operator fills that gap. They walk into a function, map how it works, and build the agent stack that runs it. No engineering degree required. Business judgment + AI execution.
Production-ready AI sales assistant for e-commerce. Handles product discovery, recommendations, and purchase flow over WhatsApp. 4-6 hour deployment per store.
View Live →Interactive visualization of Composio's tool dependency graph. Built to map how tools connect across the agent layer. 100+ Google integrations charted.
View Live →Personal knowledge OS built in Obsidian, managed via Claude Code and MCP. The operator's equivalent of a codebase — every function documented, repeatable, and improvable.
Multi-agent systems that run business functions. Prompt stacks, tool use, MCP integrations, workflow design.
Daily user. Vault management, agent deployment, system building. Operator-level fluency — no engineering required.
Meta Ads end-to-end. Campaign structure, creative testing, audience strategy, ROAS optimization.
Klaviyo flows, post-purchase sequences, LTV optimization, churn reduction. Email as a system, not a broadcast.
Shopify, MercadoLibre, marketplace ops, inventory coordination, order management at scale.
Obsidian-based knowledge management. Every function documented, repeatable, and improvable. The operator OS.
Open to remote operator roles and consulting engagements. If you're building something and need someone who can run functions with AI — let's talk.