I help Fortune 500 companies improve business outcomes with AI.
Current: Principal AI Architect at UiPath (pre-sales).
I started exploring AI agents in 2023 when the AutoGPT open-source project dropped. Since then I've been obsessed with agentic runtimes, frameworks and harnesses. I dig into code daily to understand how they work, and I use them to automate my own tasks.
Before that, I spent years in industrial process control and enterprise automation — designing systems where reliability isn't optional. I independently learned full-stack development, built custom integrations that shipped to product platforms, and trained colleagues and customers on novel technologies.
Today I build demos, prototypes that connect abstract thoughts of agentic systems to measurable business value. I think like a product manager and GTM strategist, I'm as hands-on as an FDE, and I communicate across technical audiences to the C-suite.
Walkthroughs of agent systems I've built — from design to working prototypes.
An end-to-end agentic AI workflow for wealth management — demonstrating how autonomous agents can handle client portfolio rebalancing, compliance checks, and advisor notifications. Built to show how AI agents fit into real financial services operations.
A webinar exploring how API-first architecture connects automation platforms to enterprise systems — covering integration patterns that reduce manual handoffs and accelerate revenue-generating processes.
What I'm building and experimenting with — agents, integrations, and tools.
A simple streamlit app demonstrating RAG with a custom vector store built from scratch.
Insights and perspectives on agentic AI, enterprise workflows, RAG, and governance.
Coding agents are designed to be coupled with an oracle. AI agents that automate knowledge work in business processes often cannot replicate this pattern. That is the fundamental gap that explains why coding is the flagship agent use-case, while agents for knowledge work are often still in experimentation.