DuckDB, MotherDuck, Data Engineering and Data Analytics
Search and filter
Search and filter
Topic
2026/10/01 - Alex Monahan
Data Outpost is an AI and data conference in San Francisco. Its main day, November 5, 2026, has 13 talks and panels from teams at Canva, Stripe, DoorDash, Posit, dbt and more. Here's what each session covers, from agents that write back to context layers, SQL harnesses, and AI for regulated data, and what you'll walk away with.
2026/09/29 - Mehdi Ouazza
Turn a free-text column into typed SQL columns with prompt_jev(): 100,000 consumer complaints classified in 82 seconds, at about 1% of a frontier LLM's cost, plus how to check the labels before you trust them.
2026/09/22 - Dumky de Wilde
Common Crawl publishes petabytes of web crawl data on S3. With DuckDB and MotherDuck you can query the Common Crawl dataset directly, no cluster and no download, and measure how fast the vibe-coded web is growing.
2026/09/22 - Dumky de Wilde
Common Crawl publishes petabytes of web crawl data on S3. With DuckDB and MotherDuck you can query the Common Crawl dataset directly, no cluster and no download, and measure how fast the vibe-coded web is growing.
2026/09/21 - Alex Monahan
Define your dashboards in YAML with dbt Charts, then the same dbt build that runs your pipeline deploys them to MotherDuck Dives. Just 2 config changes! Your Dives will refresh live whenever your stakeholders take a look. See how we constructed the dbt package as well.
2026/09/21 - Hamilton Ulmer, Till Döhmen, Jacob Matson
Classify text in SQL with prompt_jev(), powered by TypeSafe's Jev. 100,000 rows labeled in 40 seconds for $0.50 at frontier-LLM accuracy. Live on paid plans.
2026/09/16 - Simon Späti
The September 2026 DuckDB Ecosystem Newsletter: DuckLabs joins AWS and MotherDuck acquires Tower, DuckDB v2.0-alpha lands, table functions in pure Java, bulk loads into SQL Server, Zarr stores as SQL tables, an infinite canvas for your data, plus a community spotlight on Vladimir Gribanov.
2026/09/15 - Dumky de Wilde
SQLite, Postgres, DuckDB and 20 others: they all write, store and read data. The questions you ask every day tell you which one you need.
2026/09/14 - Kaitlyn Henry
We're launching commercial support for open-source DuckDB, so every organization can get the power of a modern data engine, with direct access to database experts.
2026/09/10 - Mehdi Ouazza
DuckDB 2.0 alpha vs 1.5.5 on one laptop: recursive CTEs up to 90x, VARIANT 6x faster than JSON text, async I/O 2.4x on S3. What changes, and how to model data to get the speedup.
2026/09/02 - Simon Späti
A primer on the context layer, semantic layer, and ontology: what each term means, how they fit together, and why AI agents still need a human to decide what's true.
2026/09/02 - Alex Monahan
We analyzed a slice of MotherDuck query history and found agents ran 29 times more queries than humans last month, a gap that has roughly doubled every month. The average organization now has twice as many agents as human users. Agents are the dominant consumers of the data platform, and our systems can't afford to stay the same.
2026/08/28 - Alex Monahan
If your laptop has 16GB of RAM, your agent can write SQL locally for free with Qwen3.8 27B. On the DABstep SQL benchmark, Qwen beat GPT 5.6 Luna and cost under 50 cents in electricity, over 17x less. Add DuckDB and you have a data analyst that runs on your own machine. This post covers the benchmark results and walks through the setup, including which quantized model to download for your laptop.
2026/08/27 - Mehdi Ouazza, MotherDuck team
Meet the MotherDuck CLI: one install to query data, publish Python pipelines, and host dashboards from your terminal, for coding agents and CI alike.
2026/08/26 - Jordan Tigani
Today Duck Labs, the developers of DuckDB, announced they are being acquired by Amazon. This is big news in the duck-iverse, and many people are wondering what this will mean for everyone’s favorite duck-powered database, MotherDuck.
2026/08/25 - Jordan Tigani
2026/08/20 - Jacob Matson, Alex Monahan
We proved that AI agents could build a semantic layer. The more interesting result was that the semantic layer itself became disposable. Q&A pairs are unreasonably effective at capturing business intent and give agents something concrete to iterate with. If code can be regenerated, where should your company accrue knowledge?
2026/08/18 - Alex Monahan
AI agents make building data apps easy, but what about deploying them or making sure they scale? Replit provides a way for just about anyone to build real applications, and MotherDuck is the easiest way to help them scale to larger data sizes. Load data with MotherDuck Flights and you can query millions to billions of rows on the fly!
2026/08/13 - Alex Monahan
Use an agent to build data apps with the combo of Vercel V0 and MotherDuck! V0 makes prototyping and deployment easy, while MotherDuck Flights provide seamless data ingestion and MotherDuck handles up to billions of rows. Your agent can even sign up for MotherDuck for you! See a full example app and the prompt that kickstarted it!
2026/08/13 - Simon Späti
The August 2026 DuckDB Ecosystem Newsletter: giving every agent its own embedded DuckDB, the ADBC extension reaching 30+ external databases, async I/O landing in v2.0, ISO GQL graph queries, Perspective 5.0 pushdown, plus a community spotlight on Kyle Cheung.
2026/08/10 - Adithya Krishnan, Sheila Sitaram, Garrett O'Brien
AI agents can now sign up for MotherDuck with a single API call - no forms, no credentials, no human in the loop (unless you want to be, of course). Experiment faster, share data, or just give your agents a ducking fast set of tools for analytics.
2026/08/04 - Mehdi Ouazza
AI agents can now provision a Postgres database, an email inbox or a data warehouse with no signup and no credit card. Here is how MotherDuck's agent signup endpoint works, and how motherduck.com/try lets you inspect, share and replay everything the agent did.
2026/08/01 - Alex Monahan, Jacob Matson
Since OpenAI slashed the price of GPT 5.6 Luna by 80% this week, low latency AI-powered answers are finally feasible for less than half a penny per answer, AI and DB costs included. For data questions, GPT 5.6 Luna is intelligence too cheap to meter. Well documented context, rigorous evals, and a fast analytical engine are now the determining factors.
2026/07/31 - Simon Späti
Maxime Beauchemin, creator of Airflow and Superset, shares how he uses AI agents for data engineering: orchestrating agents on a shared canvas with Agor, context layers and semantics, Okta for Agents security, and automating CEO work with AI assistants.
2026/07/29 - Garrett O'Brien, Hamilton Ulmer, Till Döhmen, Jacob Matson
Introducing Guides, MotherDuck's context layer for AI agents. More accurate queries, lower token spend, and distributed context for your entire organization.
2026/07/20 - Ryan Boyd
Data Outpost is a new conference for data and AI builders, coming to San Francisco November 4-5, 2026. The next evolution of Small Data SF: two days of workshops, talks, and real time with the people building the data layer AI depends on.
2026/07/16 - Alex Monahan
Waiting in line is no fun! While standing in line at Disney World, a developer dad built a custom data app to pick the perfect next ride. It combines live APIs, historical wait times, and weather data into personal software with MotherDuck's MCP, Dives, and Flights.
2026/07/15 - Simon Späti
July's DuckDB Ecosystem Newsletter: a portable R2 + DuckLake analytics stack, why PostHog rebuilt on DuckDB over ClickHouse, DuckCon #7 and the 1.5.4 / 1.4.5 releases, a SedonaDB WASM build for spatial SQL in the browser, and more.
2026/07/14 - Mehdi Ouazza
A practical map of self-hosting DuckDB, from a laptop to a full data platform: the architectures people actually build at each stage, benchmarks that show the trade-offs, and the boxes you end up maintaining, so you can make an honest build-versus-buy call.
2026/07/10 - Alex Monahan
DuckLake is a next generation data lakehouse and open table format. It is significantly simpler and faster than Apache Iceberg or Delta Lake because it uses a SQL database for storing the catalog and metadata. This post covers an architecture deep dive with a detailed Q&A section. DuckLake consists of 3 components: storage, catalog, and compute. Each can be scaled independently, hosted locally with ease, and deployed to the cloud for production. MotherDuck offers managed DuckLake lakehouses for additional simplicity and performance.
2026/07/07 - Mehdi Ouazza
AI pipelines run green and still return wrong numbers. Four habits to turn a one-shot prompt into a data pipeline you can actually trust.
2026/06/29 - Mehdi Ouazza
We launched Flights, an AI-native Python runtime in MotherDuck. Here's how I built a full end-to-end data pipeline (two scheduled Flights and a Dive dashboard) from a single prompt, using an AI coding agent and the MotherDuck MCP.
2026/06/24 - Jerel Navarrete, Jacob Matson
The DiveMaxxing winners, and what 48 community Dives taught us about what separates a great data visualization from one that just looks polished.
2026/06/18 - Alex Monahan
Build full data pipelines by prompting your AI agent, no Python required. MotherDuck Flights are perfect for data ingestion, transformation, and activation. Flight Plan templates show you and your agent how to ingest from Postgres, sync Google Sheets, and send Slack alerts.
2026/06/16 - Carlin Eng
How MotherDuck replaced its BI tool in under a month using Claude Code agents: a migration that once would have taken 3 people six months and $500K.
2026/06/12 - Simon Späti
The June 2026 DuckDB Ecosystem Newsletter: a local-first ETL/ELT studio, the Quack client-server protocol and its OAuth layer, DuckLake inlining, DuckDB internals, MotherDuck Flights for agent-native ingest, plus a community spotlight on Ryan Dolley.
2026/06/10 - Miguel Miranda, Doo Shim
Build, deploy, and schedule Python data pipelines from a prompt, a SQL function, or the MotherDuck UI.
2026/06/08 - Jacob Matson
Benchmark-maxxing DABstep to 100% and learning that an AI-native semantic layer isn't a description of your data — it's coupled to the model that reads it.
2026/06/05 - Simon Späti
Wes McKinney, creator of pandas and co-creator of Apache Arrow, shares how he works with AI coding agents: spec-driven workflows with superpowers, continuous AI code review with Roborev, token economics, and why vibe coding is dangerous but agentic engineering isn't.
2026/06/04 - Mehdi Ouazza
Run DuckDB SQL inside your Obsidian notes and freeze the results as plain markdown tables, local files or MotherDuck cloud data alike. Your vault becomes a local knowledge base your AI agent can read without ever querying the warehouse
2026/05/28 - Jerel Navarrete
DiveMaxxing is an online data viz competition for MotherDuck Dives. Three categories, duckified Mac Minis on the line, and a community vote. Free to enter through June 22.
2026/05/21 - Simon Späti
Chris Riccomini on using AI for data engineering: correctness in financial data, why LLMs should speak Substrait over SQL, the Ralph Loop for context management, security with 'Okta for Agents', and the future of the data engineer role.
2026/05/12 - Jordan Tigani
DuckDB Labs announced Quack, a client-server protocol for DuckDB. Here's why we're excited, what it means for MotherDuck, and why it's so great for the DuckDB community.
2026/05/11 - Simon Späti
DuckDB Monthly #41: Torsten's 15-week DuckDB internals course, Pete's full-text search walkthrough on a multi-GB email corpus, Mark's GCAT satellite pipeline with H3, plus column-level lineage with duck_lineage and DuckLake v1.0.
2026/04/30 - Dumky de Wilde
Track AI agent traffic that bypasses your web analytics. Stream Vercel Log Drains into MotherDuck to see how ChatGPT, Claude, and other agents browse your site.
2026/04/30 - Jacob Matson
The agent writes the SQL and the data viz now. Here's what's still your job — and how to implement data-layer changes that took a very hard natural language to SQL benchmark from 30% to 93% accuracy with Gemini Flash.
2026/04/27 - Garrett O'Brien
April 2026 at MotherDuck: Duckling compute monitoring, Embedded Dives, agent Skills, DuckLake 1.0 support, and Power BI + Tableau via the Postgres Endpoint.
2026/04/24 - Simon Späti
25 years of external tables, from Oracle 9i to DuckLake. When to use internal storage vs. external tables, why they keep getting re-added to every major data warehouse, and a benchmark showing the speed tax for cold data.
2026/04/21 - Dumky de Wilde
Build a real-time voting app on Cloudflare Workers that queries MotherDuck through the Postgres endpoint, using Durable Objects for live state and the pg package for analytical workloads.
2026/04/20 - Mehdi Ouazza, Samantha Lohier, Leonardo Vida
MotherDuck Agent Skills is an open-source catalog that teaches AI coding agents how to work with MotherDuck: exploring schemas, writing DuckDB SQL, using the REST API, and building Dives. If MCP gives agents hands, skills give them a playbook.
2026/04/17 - Simon Späti
DuckLake 1.0 ships, Lance adds vector search, Rust-native extension
2026/04/16 - Alex Monahan
MotherDuck now supports DuckLake 1.0, the open table lakehouse format designed for simplicity and low latency. Learn what's new in the 1.0 release, including data inlining, clustering, bucket partitioning, geometry and variant types, plus multi-engine support. Learn how DuckLake compares with Apache Iceberg and Delta Lake.
2026/04/15 - Jordan Tigani
In a fully agentic world, will we still need analytics at all? A particularly unhinged example might offer some clues.
2026/04/10 - Mehdi Ouazza
Five fundamental data visualization principles that transform AI-generated dashboards from pretty charts into actionable insights. Learn chart selection, design, narrative, and interactivity.
2026/04/08 - Aditya Somani
Learn how to build a text-to-SQL LLM and LangChain SQL agent with DuckDB and MotherDuck, including schema inspection, query checking, and self-correction.