#364 How to Enable Agentic Commerce with Nell Thomas, VP of Data at Shopify

2026-06-15 · Source: DataFramed · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Data Science & Analytics, Software Development & Engineering · Depth: Intermediate, extended

Summary

Nell Thomas, VP of Data at Shopify, details the emergence of "agentic commerce," where AI agents handle parts of the shopping journey from discovery to comparison. This shift necessitates a robust, invisible data infrastructure, ensuring structured product catalogs, real-time inventory, accurate pricing, and clear quality signals. Shopify is enabling this through "agentic storefronts" for merchants to connect with AI discovery services like ChatGPT, and the Shopify Catalog, which structures product data for AI. The company also co-leads the Universal Commerce Protocol (UCP) with Google and 20+ retailers to standardize agent-merchant interactions. Thomas, who leads a 400-500 person data team, stresses that while AI accelerates analysis, human accountability for data quality and objective truth-telling remains critical, requiring high-quality, well-documented data and continuous measurement of agent accuracy.

Key takeaway

For data engineers and data scientists building AI-driven commerce systems, prioritize foundational data quality and comprehensive documentation. Your role shifts to ensuring AI agents correctly interpret data, stress-testing outputs, and maintaining human accountability for insights. Invest in robust metadata and semantic layers to empower self-service analytics, allowing your team to focus on complex strategic questions requiring deep rigor and trusted outcomes.

Key insights

Agentic commerce relies on robust data infrastructure and quality, with human oversight crucial for AI agent accountability and trusted outcomes.

Principles

• Data quality is a competitive advantage for AI-driven commerce.
• AI agents require highly structured and well-documented data.
• Human accountability for AI outputs remains paramount.

Method

Shopify's approach involves structuring product catalogs, syncing inventory, ensuring pricing accuracy, and measuring data quality (latency, reliability). It uses AI to infer product attributes from images and provides an API for product data.

In practice

• Implement continuous data quality measurement and feedback loops.
• Prioritize rich metadata and documentation for all datasets.
• Utilize AI to automate product data enrichment from images.

Topics

• Agentic Commerce
• Data Quality
• AI Agents
• Shopify Catalog
• Universal Commerce Protocol
• Data Engineering

Best for: VP of Engineering/Data, AI Architect, AI Product Manager, Director of AI/ML, Data Engineer, Data Scientist

Related on AIssential

• Shopping Online Is About To Change Forever — Agentic commerce employs AI agents for proactive, personalized product discovery and visual recommendations, streamlining online shopping.
• How We Built an AI Agent for Self-Service Analytics — Effective NL2SQL for business analytics requires structured data and a semantic layer, not just connecting an LLMs to a database.
• Building an AI Agent That Turns Web Data Into Sales Intelligence — AI agents transform dynamic web data into timely, actionable sales intelligence, overcoming stale CRM data.
• Scaling Customer Experience with Operationalized Agentic AI - with Shezan Kazi of Dialpad — AI agents excel at high-volume, deterministic tasks, requiring seamless human handoff for complex or ambiguous cases.
• Presentation: What I Learned Building Multi-Agent Systems From Scratch — Specialized, lean AI agents outperform monolithic prompts, drastically reducing task times and improving efficiency.
• The Agentic Commerce Revolution — Agentic AI unbundles traditional commerce, necessitating new trust protocols for autonomous transactions.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by DataFramed.