MScAC

What does it take to design AI driven agentic systems that operate reliably for millions of merchants? Join Justin D. Harris, Senior Staff Engineer at Shopify, for an in depth look at the engineering behind Shopify’s new generation of AI powered commerce assistants. This talk explores how agents interpret merchant intent, how tool use and action orchestration are implemented at scale, and how the platform integrates with Shopify’s broader ecosystem of APIs, including GraphQL.

Drawing on real-world experience architecting production AI systems, Justin will share approaches for evaluating assistant quality in domains where correctness, safety, and business impact all matter. He will also discuss the technical and research challenges of building multi-tool agents and subagents, from everyday chat assistants to complex agentic graphs powering deep reasoning.

This session provides a unique perspective on building practical, domain specific AI assistants, and what this means for the future of applied AI in commerce.

This is a hybrid talk. To attend in person, over at the OPG building, or to attend online please register. You can find the registration links in the talk announcement here https://mscac.utoronto.ca/mscac-talks/

Bio

Justin Harris has spent over a decade building AI assistants at planet scale. As Senior Staff Engineer at Shopify, he is the tech lead for design and architecture of the agentic platform that powers many of Shopify’s AI assistants. Previously at Microsoft, he architected core components of Bing Chat and Microsoft Copilot, designing a patent-pending extension framework that serves millions of users across Edge, Windows, and M365. Earlier at Maluuba (acquired by Microsoft), he built deep learning NLP systems for conversational AI. He holds a BMath in Computer Science and Combinatorics & Optimization from the University of Waterloo.