Motherduck
Day 16 after signup
One database per customer: how Hazel does it
Hazel’s CTO on dbt-based context, agent memory, and the data stack underneath. Wed, 9:30am PT.
Why it works
- Lead with a specific event theme so readers immediately understand what the session is about.
- Build interest with a short company backstory, then make the discussion concrete with a few focused topics.
- Keep the logistics and registration call to action together so the next step is easy to find.
How it is built
- Invitation label
- Event headline
- Company story
- Guest introduction
- Discussion topics
- Event time
- Registration button
Email copy
YOU'RE INVITED Behind the Agent: How Hazel Built an AI Coworker for Consumer Brands Hazel started out predicting customer lifetime value. Then its founders saw a bigger opportunity: an AI coworker that can answer any question a consumer brand has about its business. To make that work, they had to build the data stack underneath it too. Patrik Devlin, Hazel's co-founder and CTO, joins host Alex Monahan to talk through how it's built. Bring your questions, and we'll take them live as we dig into: A separate database for every customer, on MotherDuck Context built from dbt documentation, so the agent understands the data Memory that learns from your questions over time Wednesday, Oct 21 · 9:30am PT SAVE YOUR SPOT You are receiving this email because you are subscribed to News & Updates emails from MotherDuck. You can manage your preferences or unsubscribe from all. © 2026 MotherDuck LLC. All Rights Reserved. 2811 Fairview Ave E., Seattle, WA 98104-2205