Marketing operations leader · AI systems builder
Two months after my first AI build, enterprise sellers were piloting it. Nine months in, thousands of intelligence reports had been generated in production. I’m Lily Luo. Sixteen years running B2B marketing operations, now building production agent systems at work and running my own three-agent team on my personal time.
The short version
B2B marketing operations and analytics at enterprise software companies and startups: Rocket Software, SAP Ariba, Collibra, aPriori, Icertis, now Five9. Team management, budgets, martech stacks, and campaign execution, the operational work that helps marketing execute and makes it measurable.
Less than two years ago I wrote my first Python code. Nine months in, my systems were generating account intelligence for enterprise sellers, work that earned a company-wide builder award, the first for building AI workflows. It kicked off with a single intelligence dossier and became a much larger project: how to turn manual work into tools and software, and how to leverage AI to scale and automate it.
I built The Pod, a persistent agent team that works while I sleep. I write Applied AI for Marketing Ops and lead AI workshops. Continual learning, experimenting, and hands-on practice keep me evolving, and I bring what I learn back to the business.
Selected work
Researching an account used to be slow, manual work. Now a seller triggers one workflow from the CRM and gets back a ten-section intelligence report: org chart, strategic priorities, earnings-call analysis, discovery questions, even the slides. Thousands of reports generated in production.
A marketer fills out a form and gets back multiple banner versions, in every required size, matched to the style guide, built with Azure OpenAI and Python. It feeds a larger ABM content engine that personalizes emails, LinkedIn ads, and display sets per account.
One agent audits technical SEO, files remediation tasks, and verifies the fixes live once they ship. One runs visibility reports and keyword-gap analysis. One manages social drafting and task boards. I helped solve coordination between agents and humans by leveraging the team’s existing project management tool, and it worked.
My own agent team, running 24/7 on my own infrastructure, each agent on a different model. They research, write, publish, and help me learn multi-agent systems and AI research firsthand. I also built a monitoring dashboard to assign their work, watch their status, and track what they cost.
Writing
“Practical AI implementation for operations professionals. No hype, just what actually works in corporate environments with enterprise constraints.”
I write about my journey and experience building: what works and what doesn’t. See the latest posts below.
AI promises to move as fast as your strategy changes. For that to work, you have to know what your strategy actually is.
Read on Substack →June 4, 2026Anyone can build an impressive AI output in an hour. Your edge is what only you know.
Read on Substack →May 22, 2026The dashboard I built to keep up with my agents without reading every chat message.
Read on Substack →