Dylan Berry
Founder, neurex.dev · Agentic AI training & strategy · Cloud, data & DevOps architect · 20+ years
Toronto, Canada
Actions
Dylan Berry is the founder of neurex.dev, where he trains teams and leaders to wield agentic AI tools with consistency, reliability, and precision, and helps executives set the strategy and governance around them.
He brings more than 20 years of technology consulting to the stage. Most recently he designed and built cloud data platforms on Azure and Databricks for organizations in maritime and logistics, financial services, insurance, telecom infrastructure, aerospace, cybersecurity software, and government, covering landing zones, infrastructure as code, CI/CD, data engineering, governance, and platform security. Before that he led development teams in capital markets and shipped cross-platform mobile apps.
He builds with coding agents every day, along with the tooling around them: verification gates, evaluation sets, and telemetry on cost and context usage. His talks focus on what actually holds up: context engineering, the agentic development loop, verification patterns that keep agent output trustworthy, and how leaders set AI strategy without chasing hype.
He founded the Toronto Mobile .NET Developers, a community of more than 800 developers, organized Xamarin Saturday, ran the group's weekly virtual live-coding series through 2020, and served as volunteer advisor to Centennial College's Mobile Applications Development program.
Based in Toronto. He writes at dylanberry.com.
Badges
Area of Expertise
Topics
Agentic Tools For Data Modeling in Databricks
Under most lakehouses sits a modeling problem: raw tables with cryptic column names, no keys, no comments, and three versions of every customer. Modeling is the step teams skip when deadlines get tight. AI agents change that in two directions.
First, agents can now do much of the slow work. They profile source tables, propose grain and keys, write the DDL, document every column, and build slowly changing dimensions. Second, the model you end up with decides how well every other agent performs. Genie, the Databricks Assistant and any coding agent are only as accurate as the metadata they read.
We begin with a collection of messy bronze tables and work them into a documented, tested star schema with well defined, explainable metrics. Then we step through the process: the groundwork that happens before the first prompt, the decisions a person still owns, the checks that earn trust in the agent's output, and the mistakes that shaped the final model.
You'll leave with a repeatable pattern for using agents in your modeling work, and three things to try on your own.
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top