Colab and Chill: A Vibe Coding Approach to Exploratory Data Analysis using AI

Join us for a relaxed, hands-on session where we bring the "vibe coding" philosophy to data science.

In Colab and Chill, we ditch the stress of perfect syntax and focus on the high-level "vibe" of your analysis using Google Colab’s built-in AI tools. Whether you are a coding novice or a seasoned researcher, this workshop will guide you through the rapidly evolving AI landscape—helping you distinguish between tools that "know" (like NotebookLM) and tools that "do" (like Gemini).

You will learn to master the art of prompting using the PARTS framework to drive Exploratory Data Analysis (EDA). Instead of getting bogged down in error messages, we will use AI to generate code for visualizing trends, cleaning data, and uncovering insights. Come ready to "code by conversation" and leave with a reusable workflow for any dataset.

This workshop incorporates hands-on work, and there will be plenty of time for questions. No software installation is needed.

Learning Objectives

By the end of this workshop, participants will be able to:

• Navigate the AI Landscape: Differentiate between "Knower" tools (e.g., NotebookLM for synthesis) and "Doer" tools (e.g., Gemini for execution) to select the appropriate AI assistant for specific research stages.

• Engineer Effective Prompts: Apply the PARTS framework (Persona, Aim, Recipients, Theme, Structure) to craft precise prompts that guide AI in generating relevant and tailored analysis outputs.

• Perform AI-Assisted EDA: Utilize Google Colab’s integrated AI features to programmatically explore data—generating visualizations, statistical summaries, and cleaning scripts without manual coding from scratch.

• Mitigate Hallucinations: Implement the "code generation" strategy—asking AI to write code rather than perform mental math—to ensure reproducibility and accuracy in data analysis results.