Why martech stacks optimize execution over learning

What’s up folks, today we have the pleasure of sitting down with Anthony Rotio, Chief Data Strategy Officer at GrowthLoop.

• (00:00) - Intro
• (01:10) - In this episode
• (04:05) - Journeying From Robotics to Modern Marketing Systems
• (11:05) - Most Marketing Systems Don’t Learn Because They Lack Feedback Loops
• (16:10) - The Martech Engineering Talent Gap
• (19:51) - AI Will Amplify Whoever Has the Cleanest Causal Feedback Loop
• (29:17) - Agent Context Graphs for Drift Detection in Marketing Systems
• (31:51) - Humans Will Set Hypotheses, AI Will Accelerates Iteration
• (35:50) - The Evolution of Retail Media Networks
• (45:07) - How Commerce Networks Redefine Targeting With Governed Data
• (48:26) - How Agent to Agent Commerce Operates Inside Marketing Funnels
• (53:04) - Google Universal Commerce Protocol Explained
• (54:43) - Personal Happiness System
• (56:30) - Favorite Books

Summary: Anthony traces a path from robotics and computer science to his current role where he approaches marketing as an engineering system. He explains how execution-first marketing stacks weaken feedback loops and fragment data, which slows learning and iteration. He introduces the agent context graph as a causality model that lets AI simulate and predict customer behavior with greater confidence. The conversation also covers retail media networks, first-party data monetization through governed access, and a shift toward zero-to-zero marketing driven by agent-to-agent transactions. He closes by stressing that strong data foundations determine who can compete as marketing becomes more automated and agent-driven.

About Anthony

Anthony Rotio is the Chief Data Strategy Officer at GrowthLoop, where he leads partnerships and builds generative AI product features for marketers, including multi-agent systems, AI-driven audience building, and benchmarking and evaluation work. He previously served as GrowthLoop’s Chief Customer Officer, where he built and led teams across data engineering, data science, and solutions architecture while supporting product development and strategic sales efforts.

Before GrowthLoop, Anthony spent nearly six years at AB InBev, where he led a $100M owned retail business unit with full P&L responsibility and drove major growth through operational and digital transformation work. He also led U.S. marketing for Budweiser, Bud Light, Michelob Ultra, Stella Artois, and other brands across music, food, and related consumer programs. He earned a B.A. in computer science from Harvard, played linebacker on the Harvard football team, founded the consumer product Pizza Shelf, and holds a Google Professional Cloud Architect certification.

Journeying From Robotics to Modern Marketing Systems

Anthony’s career started far away from marketing. He trained as a computer scientist and spent his early years working with robotics and reinforcement learning. His first exposure to a learning agent left a lasting impression because the system behaved less like traditional software and more like something adaptive. That experience shaped how he would later think about work, systems, and feedback. He learned early that progress comes from loops that learn, not static instructions.

That mindset followed him into an unexpected chapter at AB InBev. Anthony entered a world defined by scale, brands, and operational complexity. He treated his technical background like a carpenter treats tools, useful only when applied to real problems. Running marketing across major beer brands taught him how value is created inside large organizations. It also exposed a recurring issue. Marketing teams had ambition and data, but execution moved slowly because ideas had to travel through layers of translation before anything reached customers.

That friction became impossible to ignore. Audience definitions moved through tickets. Campaigns waited on queries. Data teams became bottlenecks through no fault of their own. Anthony felt the pull back toward technology, where systems could shorten the distance between intent and action. That pull led him to GrowthLoop, where he joined early and worked directly with customers. The appeal was immediate. The product connected straight to cloud data and removed several layers of mediation that marketing teams had accepted as normal.

As language models improved, Anthony recognized a familiar pattern. Audience building behaved like a translation problem. Marketers described people and intent in natural language, while systems demanded structured logic. Early experiments showed that natural language models could close that gap. Anthony framed the idea clearly.

“Audience building is a translation problem. You start with a business idea and you end with a query on top of data.”

Momentum followed quickly. Customers like Indeed and Google responded because speed changed behavior. Teams experimented more often and refined audiences based on results instead of assumptions. Conversations with Sam Altman and collaboration with OpenAI reinforced that this capability belonged in the core workflow. Standing on stage at Google Cloud Next marked a clear moment of validation.

That arc reshaped Anthony’s role into Chief Data Strategy Officer. His work now focuses on building systems that learn over time. Faster audience creation leads to shorter feedback loops. Shorter loops improve decision quality. Better decisions compound. The throughline from robotics to marketing holds steady. Systems improve when learning sits at the center of execution.

Key takeaway: Career leverage often comes from carrying one mental model across multiple domains. Anthony applied learning systems thinking from computer science to enterprise marketing, then rebuilt the tooling to match that mindset. You can do the same by identifying where translation slows your work, then designing interfaces that move intent directly into action. When feedback loops tighten, progress accelerates naturally.

Most Marketing Systems Don’t Learn Because They Lack Feedback Loops

Marketing organizations generate enormous amounts of activity, but learning often lags behind execution. Campaigns launch on schedule, dashboards fill with numbers, and post-campaign reviews happen right on time. The pattern repeats month after month with small adjustments and familiar explanations. Over time, teams become highly efficient at producing output while remaining surprisingly weak at retaining knowledge. The system rewards motion, visibility, and short-term lifts, which slowly conditions teams to forget what they learned last quarter.

Anthony connects this behavior to structural pressure inside large organizations. Quarterly reporting cycles dominate priorities, and executive tenures continue to compress. Leaders feel urgency to show impact quickly and publicly. Compounding growth requires early patience and repeated reinforcement, which rarely aligns with board expectations or career incentives. Short time horizons shape long-term behavior, even when everyone agrees that learning should stack over time.

“When you think about compound interest in finance, the early part looks almost linear. People want big bumps now, even if those bumps never build momentum.”

Technology choices deepen the problem. Many companies invested heavily in customer data and built impressive data clouds that capture transactions, events, and engagement in detail. Activation remains slow because teams still rely on handoffs between marketing and data groups. A familiar sequence plays out:

A marketer defines a campaign and requests an audience.
A ticket moves to a data team for interpretation and SQL.
The audience returns weeks later.
The marketer realizes the audience lacks scale for ne...