I agents are bringing a new level of automation to ad operations. Aaron Lu, AI Product Lead at Notion, shares how his team is using AI across growth marketing, building agents that automate workflows, monitor spend in real time, and enable capabilities that advertising platforms don't support natively.
Aaron explains how he decides what should become an AI agent versus a simple automation, how he builds feedback loops that improve agents over time, and what it takes to orchestrate multiple agents.
He also breaks down the competitor-monitoring system that won Profound's Marketing Engineering Hackathon and how building with parallel agents changed his workflow.
We discuss:
- How a marketer's job shifted from doing the work to designing AI systems
- Why a good cost-per-lead number can still hide wasted ad spend
- The swarm of AI agents running Notion's ad operations
- How he built an AI agent for LinkedIn dayparting, a feature the platform doesn't natively support
- The creative duplication agent that saves a day of work every week
- What he would do differently on his hackathon-winning project
- How to decide what to automate first
The Marketing Engineer is a show for practitioners figuring out in real time what it means to market at the frontier. New episodes every two weeks.
What is The Marketing Engineer?
The show for marketers who build. Marketing Engineers pair creativity with systems thinking. They have a marketer’s instincts and creativity with the technical ability to bring their ideas to life. They’re architects, agentic operators, and craftspeople with high taste.
Hear directly from practitioners and leaders who've reorganized how their teams operate, built marketing workflows for scale and quality, and invented capabilities that didn't exist before.
From Profound, the company building the workbench for the Marketing Engineer.
New episodes every two weeks.