MotherDuck Blog posts | RSS Feed

I gave an agent one instruction: load the public NOAA GHCN-Daily weather dataset and show me how temperatures across the EU have changed. It signed itself up to a cloud data warehouse, pulled the last ten years of readings...

Analytics tasks no longer need the smartest AI models. Now that even small models are as smart as prior generation flagships, new strategies open up for agentic analytics. Focusing on speed and cost over raw intelligence leads to a better user experience. If you pair a modern small model with a fast analytical database engine, low latency AI-powered answers are finally feasib...

It's hard to keep up with the AI evolution; new AI tools drop every week, but how are experienced practitioners actually using them? Most of us are overwhelmed and unsure about the many possibilities, yet we need to keep going and do our work. You might use AI agents all day long, parallelize them with AI Orchestrators, tmux, git worktree, and so on, using AI IDEs, but in the...

Today we're introducing Guides, MotherDuck's context layer for AI agents. Guides improve recall and accuracy for agent-driven data work: building pipelines, executing transformations, serving visualizations, and anything else that touches the data warehouse.

On the DABStep agentic analytics benchmark, Guides improve an agent's accuracy by 72 percentage points across an...

The next AI bottleneck isn't the model. It's the data layer the model has to act through, and that's where the hard, unsolved problems live.

That's the argument behind Data Outpost, a new conference we're bringing to San Francisco on November 4 and 5, 2026. Two days f...