Unlock high-speed data apps with the MotherDuck Wasm SDK, reducing your cloud computing costs and improving latency by running queries in your web browser. 1.5 tier architecture.
0:00so you've built a data app and your users are accessing their data from their dashboard but it's so slow well it doesn't have to be like that some architectures enables data apps to be be cheaper faster and stronger mod du can make your slow boring dashboard into instant analytics but that's not the only thing it also reduce your cloud computing gust so how
0:26is that magic happening well in a classic 3ti architecture your client a laptop would only be a light client sending commands to compute things on the cloud but because duct DB is an eded analytical database it can run anywhere including a web browser now the client is also running part of the databas and once the data is
0:52moved to the local context most user interaction won't require any communication with the cloud resulting inan lower latency and quicker performance for the user we call this the one and a half tier architecture because it combine the clients one here that know has also part of the database check out our documentation to experience our live demo and learn how
1:18to get started with dat apps and mod watch you around
43:57
2026-10-08
Mehdi Ouazza uses MotherDuck's prompt_jev() to turn text columns into columns you can GROUP BY. He classifies 100,000 consumer complaints, then walks through five use cases on real data: AI agent logs, Hacker News sentiment, sales calls, and two kinds of job-ad analysis.
Stream
MotherDuck Features
AI ML and LLMs
51:58
2026-10-01
Jacob Matson walks through a working data chat agent he built: MCP tools, an agentic loop, a tuned system prompt, hard-coded read-only guardrails, and telemetry. He demos it live against a real dataset, walks through the actual codebase, then shows the same backend re-platformed into a Slack bot.
Stream
MotherDuck Features
AI ML and LLMs
Data Pipelines
49:02
2026-09-29
MotherDuck's new prompt_jev() function runs text classification directly from SQL using Jev, a decision-focused model from typesafe.ai. In a live demo, Jacob Matson, Dumky de Wilde, and Hamilton Ulmer showed it filtering, disambiguating, and re-ranking real data without leaving SQL. The number they kept coming back to: 100,000 rows classified at 89% accuracy in 40 seconds, compared to 32 minutes and $37.58 for a comparable LLM call.
Stream
MotherDuck Features
AI ML and LLMs
Data Pipelines