Skip to content
UsecaseBoard
← All use cases
Hashnodelearning

Practice SQL on coffee sales with an AI tutor

At a glance

A learner used Qwen to generate SQL exercises and explain errors while working in a Kaggle notebook. This workflow is listed under learning, SQL, data analysis.

Agents / tools
Qwen, Kaggle, pandas, pandasql

SourceBuilding a tool for these workflows? See weekly rates.

What they did

1) Open a Kaggle Jupyter notebook with the coffee-orders dataset and make pandas and pandasql available. Import pandas as pd and sqldf from pandasql, then load the coffee sales CSV into a DataFrame named df. 2) Give Qwen the dataset and ask for five basic SQL practice questions. 3) Write a query in a notebook cell and run it with sqldf: for example, select rows from df where Weekday is 'Fri'. 4) Inspect the result; if the query fails, share the error with Qwen and work through its explanation before trying the next exercise. The author moved from requesting solutions to attempting them herself first.

Worth knowing

One published exercise asks for the most transactions, but its example query sums money instead; check that a query measures the intended quantity.

Save ideas in this browser. Upvotes count across the board.

Prompt excerpt

No prompt excerpt was provided by the source.

Sponsored

CodeBuddy

Tencent Cloud AI coding assistant for IDE and CLI.

Try CodeBuddy ↗
Explore all →