MotherDuck Acquires Tower to power Data AgentsRead
Stay up to date with our next events around the globe. Online and IRL.
Search and filter
Search and filter
Location
Type
A livestream on how the new query_rw tool in the MotherDuck MCP server gives agents write access to your warehouse, so they can save derived tables and intermediate results.
Online - 4:30 PM Coordinated Universal TimeThis webinar walks through building a conversational AI layer for a SaaS product using the MotherDuck MCP server. We'll cover the full loop: connecting an LLM to live user data with read-only scoped access, building a streaming chat backend that handles sequential tool calls, adding custom visualization tools inside the conversation, and isolating customer data with MotherDuck's hypertenancy architecture. You'll leave with a reusable pattern you can drop into your own product.
Online - 4:00 PM Coordinated Universal TimeMotherDuck's Till Döhmen speaks on Context Engineering for MCP Servers at this one-day Python AI conference for builders shipping AI to production.
Shack15, Ferry Building, San Francisco, CA - 9:00 AM America, Los AngelesBuild & ship a real app with AI using Lovable — no coding needed. Led by Ros Bernstein & Sally Revell. Perks: free Lovable access, $100 Claude API tokens, $250 Stripe credits. Open to all — bring a laptop, your best ideas & curiosity!
MotherDuck HQ, Seattle, Washington - 12:00 PM America, Los AngelesTwo-day technical conference at Belmont University in Nashville, built by the data community for roughly 500 attendees. Tracks cover AI and data science (LLMs, RAG, model eval), modern data engineering (pipelines, streaming, platform design), analytics storytelling (dashboards, BI, business impact), and careers/leadership. Stop by the MotherDuck expo table and catch Jacob Matson's session on multiplying data engineering throughput with MotherDuck and AI — "Clone, Code, Ship."
Nashville, Tennessee - 8:00 AM America, ChicagoThe flock flies through Nashville! Join MotherDuck for an invite-only evening of drinks, bites & conversation at Puttshack during DataTune. Connect with speakers, engineers, and data leaders over cocktails and tech-infused mini golf.
Puttshack - Nashville, 138 12th Ave N, Nashville, TN 37203 - 5:30 PM America, ChicagoThree talks on what AI actually gets wrong in practice. Vaibhav Gupta from BAML argues that Python and TypeScript weren't designed for the agent world and shows what he'd do differently. Jacob Matson from MotherDuck makes the case that your agent should write SQL so you don't have to. Mikayla Maki from Zed covers programming with agents from inside the editor. Talks start at 6:30, followed by open networking with speakers and other builders. At Boundary's space in downtown Seattle.
Seattle, WA - 6:00 PM America, Los AngelesData teams field the same questions over and over — "what were last month's numbers," "break this down by region," "compare Q3 to Q4." We built Dives to fix that. Ask your AI agent a question, get an interactive visualization backed by live data, and save it to your workspace. Same question next week? The answer's already there. Join us to see how it works.
Online - 5:00 PM Coordinated Universal TimeFive talks on Apache DataFusion and what's happening around it in data infrastructure. Xiangpeng Hao from UW-Madison covers pushdown caching with LiquidCache. Bev Turnbaugh from MotherDuck presents DuckLake and what a next-generation lakehouse looks like. Zac Farrell from Hotdata pairs DataFusion with DuckLake, LakeSail's Shehab Amin demos native Iceberg and Delta Lake support, and Embucket's founders walk through DataFusion infrastructure internals. Hosted at Chroma in SF with food and networking from 5:30.
San Francisco, CA - 5:30 AM America, Los AngelesWe'll walk through turning Slack conversations into a queryable knowledge base using real-time data pipelines. Jonathan Wihl from Estuary will show how streaming data flows into MotherDuck without batch processing, and Jacob Matson from MotherDuck will cover metadata enrichment techniques that improve text-to-SQL accuracy — going beyond traditional foreign keys to surface hidden relationships in your data. Expect working demos, not slides.
New York City, USA - 6:00 PM America, New YorkThe first DuckDB Developer Meeting, held in Amsterdam, brings together engineers building DuckDB extensions and complex applications on top of DuckDB. Talks cover extension development, internal architecture, and real-world use cases from people working directly on or deeply integrated with the DuckDB codebase. Organized by DuckDB Labs with MotherDuck participation.
Amsterdam, Netherlands 🌷 - 4:00 PM Europe, AmsterdamAlex Monahan from MotherDuck presents at HalfStack Phoenix on rendering data visualizations at 200 FPS using open source libraries — slicing through millions of rows in the browser in about 5 milliseconds. HalfStack is a 200-person web and JavaScript conference at the Majestic Theater in Gilbert, AZ, with sessions on accessibility, AI-driven UIs, NFC hardware hacking, and in-browser data processing. No vendor pitches.
Phoenix, AZ - 10:00 AM America, PhoenixAn afternoon meetup in Amsterdam with the teams behind MotherDuck, dltHub, and Marimo. Live demos show how these three tools connect in practice: dltHub for Python-native data ingestion pipelines, MotherDuck for serverless DuckDB analytics in the cloud, and Marimo for reactive Python notebooks. Early users share how they've wired the stack together, followed by open discussion on where the ecosystem is headed.
Amsterdam, Netherlands 🌷 - 3:00 PM Europe, AmsterdamMost data warehouses aren't set up with AI agents in mind. This webinar covers what it actually takes to prepare your warehouse so LLMs and AI agents can query it reliably — from metadata enrichment and column naming conventions to access patterns that work with text-to-SQL. Practical steps you can take now, not a roadmap pitch.
Online - 5:30 PM Coordinated Universal TimeThe third installment of The MCP Sessions — a live, unscripted format where two people query a dataset using the MotherDuck MCP server and talk through what they find. This volume focuses on clickstream data: page views, session paths, conversion funnels, and user behavior patterns. No slides, no prep — just SQL queries run through natural language against real data, with commentary on what the results mean.
Online - 7:30 PM Coordinated Universal TimeTwo-day community data conference in Austin. MotherDuck sponsors the database track, and DuckDB co-creator Hannes Muhleisen runs an open AMA. Sessions range from Bill Inmon on data architecture to hands-on workshops on data contracts, BAML for AI agents, and knowledge graphs. Other talks cover AI-ready data with semantic layers, solopreneur data businesses, and why finance kills AI projects. About 15 sponsors and a broad mix of data engineering, analytics, and AI content.
Austin, Texas - 9:00 AM America, ChicagoThe second MCP Sessions — same unscripted format, different dataset. This time we dig into supply chain data using the MotherDuck MCP server: inventory levels, shipping timelines, supplier performance, and bottleneck analysis. Two people, natural language queries, real data, and a running conversation about what the numbers actually tell you. No slides.
Online - 7:30 PM Coordinated Universal TimeText-to-SQL benchmarks top out around 78% accuracy — not good enough when business decisions depend on the answer. Ryan Boyd walks through what it takes to close that gap and make LLM-powered analytics actually reliable. Covers the failure modes that trip up AI agents on real business data, the metadata and schema patterns that improve accuracy, and how MotherDuck approaches the problem differently.
Online - 5:30 PM Coordinated Universal TimeThe first MCP Sessions — a live format where two people explore a dataset using the MotherDuck MCP server with no slides or prep. Volume 1 focuses on sports data: player stats, team comparisons, historical trends, and whatever questions come up in the moment. Natural language queries go in, SQL runs on MotherDuck, and the conversation follows wherever the data leads.
Online - 7:30 PM Coordinated Universal TimeHands-on workshop where you build a serverless lakehouse from scratch using DuckLake. Covers setting up DuckLake on MotherDuck, ingesting data, running analytical queries, and understanding how DuckLake handles metadata and storage differently from traditional lakehouse formats like Iceberg and Delta Lake. You write the queries and follow along — not a demo you watch.
Online - 6:00 PM Coordinated Universal Time