Skip to main content

Jev for Analytics: 5 Use Cases on Real DataLivestream Oct. 8

MotherDuck in 100 seconds (by a duck 🦆)

2023/10/31

A duck gives you a fast-paced tour of MotherDuck product capabilities and features.

0:00ready to dive into modu the SS analytics platform based on Duck DB in 100 seconds hold on you don't know what tuckdb tuckdb is an unbeaded open- Source analytical database it's so lightwe that it's super easy to install and support multiple interfaces in a few seconds you are ready to Crunch your data using SQL pleasingly fast duck DB shines in local

0:26data analytics while mod du elevates simly is to the cloud offering a power pack platform for your next gen cloud data warehouse or data apps anywhere you can run duct TV you can run mother duck with just a few lines to authenticate the mother duck UI gives you an easy way to explore and upload your data The

0:47Notebook enables you to write SQL queries and get rapidly valuable Insight you can also create data that sit directly on your object storage like ads S3 Google cloud storage or AZ your blob storage once your data is in mdck it's easy to share it with others in a few clicks you can get a share URL to pass

1:10to Du user and start query hybrid query execution is a stand out feature of mod duck leveraging duct DBS in bided nature that allows it to run locally together they form a dynamic duo mod duck smartly orchestrated tasks deciding whether data is processed locally byb or in the cloud this PS up the processing but also saves on cloud expenses finally mod dark

1:34integrates with a lot of common tools from the mod data stack or should I say the duck St if you have more question paddle over our documentation website and don't hesitate to join our community slack group so don't be shy and Quack away

Related Videos

"Virtual Workshop: Build a Data Agent in 60 Minutes" video thumbnail

51:58

2026-10-01

Build a Data Agent in 60 Minutes

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

"We Classified 100,000 Rows in 40 Seconds: Introducing prompt_jev()" video thumbnail

49:02

2026-09-29

prompt_jev(): SQL-Native Text Classification

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