MOTHERDUCK BLOG
MOTHERDUCK BLOGDuckDB, MotherDuck, Data Engineering and Data Analytics
Search and filter
Search and filter
Topic
2026/03/24 - Alex Monahan
Don't Fear the Agents - AI on the Data Lakehouse
Learn how MotherDuck's Hosted DuckLake combines lakehouse scale (borrowing the best ideas from Apache Iceberg and Delta Lake) with low latency and agent sandbox isolation, making it the simplest data lakehouse for AI-powered agentic workflows.
2026/03/23 - Jordan Tigani
Future Casting the Modern Data Stack
If the Modern Data Stack isn't yet dead, it's at least incredibly sleepy. AI is bringing the "long run" closer than ever — here's what might come next for ETL, BI, data warehouses, and the role of data engineers.
2026/03/19 - Garrett O'Brien
Claudeception: Inside the Mind of an Analytics Agent
More tool calls, more schema exploration, more verification — does it help, or hurt? We dug into the chain-of-thought traces behind one of the hardest text-to-SQL benchmarks to understand how analytics agents actually think.
2026/03/19 - Garrett O'Brien
Claudeception: Inside the Mind of an Analytics Agent
More tool calls, more schema exploration, more verification — does it help, or hurt? We dug into the chain-of-thought traces behind one of the hardest text-to-SQL benchmarks to understand how analytics agents actually think.
2026/03/13 - Simon Späti
DuckDB Ecosystem Newsletter – March 2026
SQL Transpilers, VS Code Extensions, Dives and more
2026/03/09 - Alex Monahan
DuckDB 1.5 Features I am Excited About
DuckDB 1.5 is both faster and easier to use! JSON analysis can be up to 100x faster thanks to the VARIANT type and JSON shredding. Real-world queries are faster, including both basic and complex queries. Writes to Azure are supported, and checkpoint concurrency is dramatically improved.
2026/03/06 - Mehdi Ouazza
What is MCP? A Data Person's Guide to Agentic Analytics
MCP explained for data people: what it is, how it works, and how to connect your AI agent to your databases and tools
2026/03/05 - Garrett O'Brien, Louisa Huang
Dashboards as Code : CI/CD For MotherDuck Dives
Local development, version control, and automated CI/CD deployments for MotherDuck Dives — composable data visualizations that are just code.
2026/03/03 - Garrett O'Brien
Give Your Agents Write Access
The MotherDuck remote MCP server now supports write operations. Learn how zero-copy clones, snapshots, and hypertenancy make it safe to let agents build in your data warehouse.
2026/03/02 - Alex Monahan
Claude Code + Dives = Any data UI
Learn how to build custom interactive data visualizations using MotherDuck Dives and Claude Code. From setup to sharing, create refreshable React and SQL-powered visuals with natural language prompts.
2026/02/25 - Jacob Matson
How I dive - Claude.ai Edition
Explore first, find the story, iterate on the artifact, test in MotherDuck. The workflow I keep coming back to after weeks of building.
2026/02/24 - Simon Späti
Git for Data Applied: Comparing Git-like Tools That Separate Metadata from Data
Comparing Git-like Tools That Separate Metadata from Data
2026/02/19 - Jordan Tigani
Duck, Dive, and Answer
AI is eating the data stack. Introducing Dives, a new MotherDuck feature that lets AI agents build shareable, real-time data visualizations with composable SQL.
2026/02/11 - Simon Späti
DuckDB Ecosystem Newsletter – February 2026
MSSQL Extension, Vortex File Format & 2TB Memory Benchmarks
2026/02/06 - Jacob Matson
Does "AI-Ready Data" simply mean "Good Data Modeling"?
I ran 500 text-to-SQL questions against three frontier LLMs with zero context beyond the schema. 95% accuracy. No semantic layer required.
2026/02/05 - Simon Späti
Building an Obsidian RAG with DuckDB and MotherDuck
Build a local-first RAG for your Obsidian notes using DuckDB's vector search, then deploy it as a serverless web app with MotherDuck
2026/02/04 - Sheila Sitaram, Joseph Hwang, Nicholas Greenspan
More Control, Less Hassle: Self-Serve Recovery with Point-in-Time Restore
MotherDuck now supports point-in-time restores, making it easier than ever to roll back changes, undrop databases, and debug pipelines.
