AI-Powered Pandas Practice Workshop

Length: 1 day

Description

The AI revolution is here. Engineers at major companies are now using AI instead of writing code directly.

But there’s a gap: Most developers know how to write code OR how to prompt AI, but not both. When working with real data, vague AI prompts produce code that might work on sample datasets but creates silent errors, performance issues, or incorrect analyses with messy, real-world data that requires careful handling.

My AI-Powered Pandas Practice Workshop is a hands-on session where you’ll solve real problems using Claude Code, then learn to critically evaluate and improve the Python code it produces. You’ll improve your Python skills and your agent-coding skills and your data-analysis skills — all at the same time.

This course consists of about 5 exercises. For each exercise, you’ll be expected to use Claude Code to write the Python and Pandas code for you, rather than write it yourself. You’ll then examine the output, see what (if any) improvements you need to give Claude, and iterate until you have a solution. We’ll compare notes on prompts, configuration, and Python output, giving everyone a chance to improve their skills.

The exercises will use real-world data, and will sometimes involve libraries with which you have less experience, such as Polars, Marimo, and Plotly.

Let’s talk about how to customize this course for your team! Set a meeting at https://savvycal.com/reuven/corp-training.

Audience

Employees who are comfortable with analyzing data with Python and Pandas, and now want to move into using agent-based data-analysis coding with Claude Code.

Sample exercise topics

• Retrieving data from the Internet in a variety of formats

• Combining a number of data sets into a single data frame

• Cleaning data

• Optimizing queries and memory usage

• Using PyArrow

• Moving from Pandas to Polars, and comparing the results

• Using Marimo for data dashboards and displays

• Using Plotly for interactive graphics displays

•