Skip to main content

MOTHERDUCK BLOG

MOTHERDUCK BLOG

DuckDB, MotherDuck, Data Engineering and Data Analytics

Search and filter

Search and filter

Topic

Introducing Flight Explainer: Live charts of your python pipelines

Introducing Flight Explainer: Live charts of your python pipelines

Nov 2, 2026 • Colin Rogers, Hamilton Ulmer

Agents can build a MotherDuck Flight in minutes. But how do you know it does what you asked? Flight Explainer is EXPLAIN ANALYZE for your pipelines: a live chart of every run showing the plan, which branch it took, how far each step got, and what it touched.

Introducing Dive Apps: Superpowers for AI Builders

Introducing Dive Apps: Superpowers for AI Builders

Oct 29, 2026 • Alex Monahan

MotherDuck is launching Dive Apps: fully custom data apps that can write-back anywhere. Build them with your agent and they run on the MotherDuck data warehouse. Use Dive Apps to replace SaaS apps, automate your operations, or bring humans into the loop to steer your agents.

Introducing Dive Apps: Superpowers for AI Builders

Introducing Dive Apps: Superpowers for AI Builders

Oct 29, 2026 • Alex Monahan

MotherDuck is launching Dive Apps: fully custom data apps that can write-back anywhere. Build them with your agent and they run on the MotherDuck data warehouse. Use Dive Apps to replace SaaS apps, automate your operations, or bring humans into the loop to steer your agents.

Bringing the Big Ducks

Bringing the Big Ducks

Oct 28, 2026 • Jordan Tigani

The pursuit of all things duck-related has led us to some interesting places. In this blog, MotherDuck CEO Jordan Tigani explores the bigger, darker corners of benchmarks on top DuckDB 1.5 (and teases what is possible in DuckDB 2.0).

DuckDB Ecosystem Newsletter : October 2026

DuckDB Ecosystem Newsletter : October 2026

Oct 18, 2026 • Simon Späti

The October 2026 DuckDB Ecosystem Newsletter: Jev typed AI answers in DuckDB and MotherDuck SQL, DuckDB 2.0's PEG parser and async S3 reads, DuckLake maintenance, analysis-ready OpenStreetMap, OneLake in the browser, a native Mac app, plus a community spotlight on Mark Litwintschik.

prompt_jev() now works on images

prompt_jev() now works on images

Oct 16, 2026 • MotherDuck team

prompt_jev() now takes images: store them as BLOBs in MotherDuck, ask closed questions in SQL, and get typed answers with a confidence score you can join with the rest of your data.

MotherDuck is coming to Azure

MotherDuck is coming to Azure

Oct 15, 2026 • Jacob Matson

MotherDuck is coming to Azure. Pick your region on the waitlist; regions open in order of demand. Your Copilot agents can connect to MotherDuck today.

A Chief of Staff's Guide to Context Layers

A Chief of Staff's Guide to Context Layers

Oct 15, 2026 • Kaitlyn Henry

Kaitlyn, MotherDuck’s Chief of Staff, on why self-serve analytics with AI agents fragments your metrics, and how non-technical leaders can get everyone on one definition of metrics.

Data Engineering Is the Cache Invalidation Problem ft. Josh Wills

Data Engineering Is the Cache Invalidation Problem ft. Josh Wills

Oct 9, 2026 • Simon Späti

Josh Wills, creator of dbt-duckdb and former head of data engineering at Slack, on why the model barely matters, why agents still write ugly and expensive data pipelines, and why data engineering is still the cache invalidation problem.

Build It Yourself: What You'll Make at the Data Outpost Workshops

Build It Yourself: What You'll Make at the Data Outpost Workshops

Oct 5, 2026 • Alex Monahan

Data Outpost kicks off on November 4, 2026 in San Francisco with 11 hands-on workshops from MotherDuck, Vercel, Sigma, Prefect, Estuary, Airbyte, Reducto, Braintrust, and Together AI. Here's what you'll build in each one: your own agents, the data pipelines they need, and the skills to run them in production.

AI Needs Data, Data Needs AI: What You'll Learn at Data Outpost

AI Needs Data, Data Needs AI: What You'll Learn at Data Outpost

Oct 1, 2026 • 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.

Querying the entire internet with MotherDuck

Querying the entire internet with MotherDuck

Sep 22, 2026 • 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.

dbt Charts on MotherDuck: Declarative Dashboards

dbt Charts on MotherDuck: Declarative Dashboards

Sep 21, 2026 • 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.

DuckDB Ecosystem Newsletter : September 2026

DuckDB Ecosystem Newsletter : September 2026

Sep 16, 2026 • 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.

Why DuckDB 2.0 is faster

Why DuckDB 2.0 is faster

Sep 10, 2026 • 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.

Agents Don’t Query Like Humans Do

Agents Don’t Query Like Humans Do

Sep 2, 2026 • 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.

Agentic SQL for Free with Qwen3.8 27B and DuckDB

Agentic SQL for Free with Qwen3.8 27B and DuckDB

Aug 28, 2026 • 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.

DuckDB outgrows its nest

DuckDB outgrows its nest

Aug 26, 2026 • 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.

AI Writes the Semantic Layer

AI Writes the Semantic Layer

Aug 20, 2026 • 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?

Scalable Data Apps with MotherDuck & Replit

Scalable Data Apps with MotherDuck & Replit

Aug 18, 2026 • 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!

Vibe Code Data Apps with Vercel V0 & MotherDuck

Vibe Code Data Apps with Vercel V0 & MotherDuck

Aug 13, 2026 • 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!

DuckDB Ecosystem Newsletter : August 2026

DuckDB Ecosystem Newsletter : August 2026

Aug 13, 2026 • 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.

Agents can sign up for MotherDuck

Agents can sign up for MotherDuck

Aug 10, 2026 • 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.

OpenAI Just Made Analytics 10x Cheaper

OpenAI Just Made Analytics 10x Cheaper

Aug 1, 2026 • 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.

Context belongs in the warehouse

Context belongs in the warehouse

Jul 29, 2026 • 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.

Announcing the Data Outpost Conference

Announcing the Data Outpost Conference

Jul 20, 2026 • 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.

Developer Dad Does Disney: Vacationing in the Personal Software Era

Developer Dad Does Disney: Vacationing in the Personal Software Era

Jul 16, 2026 • 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.

DuckDB Ecosystem Newsletter : July 2026

DuckDB Ecosystem Newsletter : July 2026

Jul 15, 2026 • 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.

Self-hosting DuckDB: the road to production

Self-hosting DuckDB: the road to production

Jul 14, 2026 • 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.

DuckLake Architecture Deep Dive

DuckLake Architecture Deep Dive

Jul 10, 2026 • 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.

What if a full data platform was one prompt away?

What if a full data platform was one prompt away?

Jun 29, 2026 • 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.

Flight Plans: Templates for AI-Native Data Pipelines

Flight Plans: Templates for AI-Native Data Pipelines

Jun 18, 2026 • 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.

Replacing Our BI Tool with Dives

Replacing Our BI Tool with Dives

Jun 16, 2026 • 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.

DuckDB Ecosystem Newsletter : June 2026

DuckDB Ecosystem Newsletter : June 2026

Jun 12, 2026 • 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.

Vibe Coding Is Dangerous, Agentic Engineering Isn't ft. Wes McKinney

Vibe Coding Is Dangerous, Agentic Engineering Isn't ft. Wes McKinney

Jun 5, 2026 • 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.

Your Obsidian Vault Can Now Run SQL (and Your Agent Can Read It)

Your Obsidian Vault Can Now Run SQL (and Your Agent Can Read It)

Jun 4, 2026 • 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

AI Agent Analytics with Vercel & MotherDuck

AI Agent Analytics with Vercel & MotherDuck

Apr 30, 2026 • 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.

Vibe Coding has come for BI

Vibe Coding has come for BI

Apr 30, 2026 • 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.

MotherDuck on Cloudflare Workers

MotherDuck on Cloudflare Workers

Apr 21, 2026 • 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.

MotherDuck Skills: Teaching Your AI Agents to Do Analytics

MotherDuck Skills: Teaching Your AI Agents to Do Analytics

Apr 20, 2026 • 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.

Announcing DuckLake 1.0 on MotherDuck

Announcing DuckLake 1.0 on MotherDuck

Apr 16, 2026 • 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.

Consulting the Oracle: Claude on the Future of Data

Consulting the Oracle: Claude on the Future of Data

Apr 3, 2026 • Jordan Tigani

What does AI think its own impact will be on the data and analytics industry? I asked Claude to share its predictions on the Modern Data Stack, data jobs, and the future of analytics.

MotherDuck Now Speaks Postgres

MotherDuck Now Speaks Postgres

Mar 31, 2026 • Louisa Huang, Jelte Fennema-Nio, Sheila Sitaram, Garrett O'Brien

MotherDuck's Postgres endpoint lets you query your data warehouse using any PostgreSQL-compatible client, driver, or BI tool — no new dependencies needed.

Specs Over Vibes: Consistent AI Results ft. Mark Freeman

Specs Over Vibes: Consistent AI Results ft. Mark Freeman

Mar 27, 2026 • Simon Späti

Mark Freeman, Head of DevRel at Gable, shares his Spec-Driven Development workflow for producing high-quality, reproducible AI outcomes using Claude Code, ExcaliDraw diagrams, JSON schemas, and agent teams with tmux.

Don't Fear the Agents - AI on the Data Lakehouse

Don't Fear the Agents - AI on the Data Lakehouse

Mar 24, 2026 • Alex Monahan

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.

Future Casting the Modern Data Stack

Future Casting the Modern Data Stack

Mar 23, 2026 • Jordan Tigani

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.

Claudeception: Inside the Mind of an Analytics Agent

Claudeception: Inside the Mind of an Analytics Agent

Mar 19, 2026 • Garrett O'Brien

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.

DuckDB 1.5 Features I am Excited About

DuckDB 1.5 Features I am Excited About

Mar 9, 2026 • Alex Monahan

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.

Dashboards as Code : CI/CD For MotherDuck Dives

Dashboards as Code : CI/CD For MotherDuck Dives

Mar 5, 2026 • Louisa Huang, Garrett O'Brien

Local development, version control, and automated CI/CD deployments for MotherDuck Dives — composable data visualizations that are just code.

Give Your Agents Write Access

Give Your Agents Write Access

Mar 3, 2026 • Garrett O'Brien

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.

Claude Code + Dives = Any data UI

Claude Code + Dives = Any data UI

Mar 2, 2026 • Alex Monahan

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.

How I dive - Claude.ai Edition

How I dive - Claude.ai Edition

Feb 25, 2026 • Jacob Matson

Explore first, find the story, iterate on the artifact, test in MotherDuck. The workflow I keep coming back to after weeks of building.

Duck, Dive, and Answer

Duck, Dive, and Answer

Feb 19, 2026 • Jordan Tigani

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.

SQL Golf: Lessons from Quackmas 2025

SQL Golf: Lessons from Quackmas 2025

Jan 23, 2026 • Jacob Matson

From #N column references to boolean math, explore the extreme techniques used to solve the Quackmas 2025 SQL Golf challenge.

This Month in the DuckDB Ecosystem: January 2026

This Month in the DuckDB Ecosystem: January 2026

Jan 17, 2026 • Simon Späti

DuckDB news: Iceberg extension adds full DML (INSERT/UPDATE/DELETE). Process 1TB in 30 seconds. Query data via AI agents with MCP server. TypeScript macros for APIs.

What If We Don't Need the Semantic Layer?

What If We Don't Need the Semantic Layer?

Dec 23, 2025 • Jacob Matson

What if AI could discover your business logic by mining query history instead of requiring manual metric definitions? Explore how LLMs are replacing static semantic layers with systems that learn from actual usage.

A Quack-Packed Fall

A Quack-Packed Fall

Dec 22, 2025 • Carly Spoljaric, Jerel Navarrete

MotherDuck spent fall on the conference circuit across Europe and the US. Here's what we presented and the pattern that emerged in nearly every conversation about analytics.

Stop Paying the Complexity Tax

Stop Paying the Complexity Tax

Dec 19, 2025 • Ryan Boyd

My personal reflections from watching Jordan Tigani’s keynote "The Unbearable Bigness of Small Data" at Small Data SF. Most data warehouses are overbuilt for scale you'll never need. Learn how to stop paying the complexity tax.

Building an answering machine

Building an answering machine

Dec 17, 2025 • Jordan Tigani

Discover how MotherDuck's MCP server enables true self-service analytics through AI agents. Query data in plain English with Claude, ChatGPT, or Gemini—no SQL required.

MotherDuck Integrates with PlanetScale Postgres

MotherDuck Integrates with PlanetScale Postgres

Dec 16, 2025 • Garrett O'Brien, Jacob Matson

Run analytics 200x faster on PlanetScale Postgres with MotherDuck integration. Keep millisecond transactions while pushing analytical queries to serverless compute.

This Month in the DuckDB Ecosystem: December 2025

This Month in the DuckDB Ecosystem: December 2025

Dec 10, 2025 • Simon Späti

DuckDB news: v1.4 adds AES-256 encryption. DuckLake brings ACID-compliant lakehouse with time-travel queries. Gaggle extension queries Kaggle datasets directly via SQL.

Branch, Test, Deploy: A Git-Inspired Approach for Data

Branch, Test, Deploy: A Git-Inspired Approach for Data

Nov 24, 2025 • Simon Späti

This article explores how to bring Git style workflows like branching, testing, and deploying to your data stack. Learn how concepts like zero copy cloning and metadata pointers can finally give you isolated test environments.

Small Data SF 2025: the Recap!

Small Data SF 2025: the Recap!

Nov 14, 2025 • Garrett O'Brien

Dive into a recap of the world's hottest efficiency-themed data conference, Small Data SF!

DuckDB Ecosystem: November 2025

DuckDB Ecosystem: November 2025

Nov 12, 2025 • Simon Späti

DuckDB news: QuackStore caching cuts query time from 49s to 3s. Infera runs ONNX ML models in SQL. 127 community extensions analyzed. DuckLake architecture explained.

Faster Ducks

Faster Ducks

Oct 28, 2025 • Jordan Tigani

Benchmarks, efficiency, and how MotherDuck just got nearly 20% faster.