Unlock AI Superpowers for Data Pros
Published by O'Reilly Media, Inc.
From coding to agents
What you’ll learn and how you can apply it
- Use AI tools like ChatGPT to produce working code snippets for specific tasks
- Apply best practices and evaluate AI-generated code for security risks
- Use AI as a tool to augment your own knowledge
- Save time creating data visualizations, models, and transformations with AI assistance
- Learn to identify AI pitfalls and verify outputs, ensuring reliable and safe application in production environments
Course description
Generative AI tools like ChatGPT, Cursor, Claude, Gemini, and others have gotten so effective at writing code that data scientists and software developers are rethinking their workflows. These tools can help you boost productivity, prototype faster, and learn from generated examples, but they’re not a license to vibe code.
Join expert Thomas Nield to discover how to wield AI tools responsibly. You’ll explore practical applications in data science, software development, and troubleshooting. Through hands-on exercises and real-world demos, you’ll discover a wide range of tasks AI can help tackle, from generating Matplotlib charts to performing complex refactoring. You’ll dive into AI pitfalls, learning verification techniques and best practices to ensure your projects remain secure and robust. You’ll also get the rundown on AI agents and why they’re a logical next step in formalizing your workflow.
This live event is for you because...
- You’re a data science professional who wants to streamline your workflow with AI tools.
- You’re a data engineer who’s looking to stay ahead of the curve with new tools and frameworks.
- You’re an analyst who’s curious how AI can help you get insights from data more quickly.
Prerequisites
- Python 3.8+ and pip installed on your machine
- Familiarity with Python (e.g., variables, loops, functions) or another programming language
Recommended follow-up:
- Read Hands-On Large Language Models (book)
- Read AI and ML for Coders in PyTorch (book)
- Read The AI Pocket Book (book)
Schedule
The time frames are only estimates and may vary according to how the class is progressing.
Why use AI? (15 minutes)
- Group discussion: Your experiences coding with AI
- Presentation: Using AI for data science and development
- Q&A
Ground rules with AI (45 minutes)
- Group discussion: What makes AI “safe”?
- Presentation: Pitfalls and weaknesses; verification and common sense; trust and security; value of IDEs; the viral RNN mistake
- Group discussion: Vibe coding
- Hands-on exercise: Lightning round
- Q&A
- Break
Using AI for data science (60 minutes)
- Demonstration: Getting help making a Python venv; generating pandas, Matplotlib, and Manim code; converting R code into Python code; converting math LaTeX; surfacing biases
- Presentation: Study and learn, then “vibe”
- Hands-on exercise: Convert TensorFlow to PyTorch
- Q&A
- Break
Using AI for data pipelines (30 minutes)
- Demonstration: Migrating SQLite to PostgreSQL; converting an SQL query into JSON; distributing data with FastAPI; turning matplotlib into D3.js
- Group discussion: What are security red flags?
- Hands-on exercise: Explore data pipeline backend in Python
- Q&A
Using AI to troubleshoot (30 minutes)
- Demonstration: Refactoring; debugging scripts; surfacing security issues; writing better, faster code
- Q&A
- Break
Building your own AI agents (50 minutes)
- Presentation: Turning a workflow into a tool; why AI agents are a next step; proprietary or OSS?
- Demonstration: Simple AI agent examples; calling Python functions from an agent
- Hands-on exercise: Build an SQL translator
Wrap-up and Q&A (10 minutes)
Your Instructor
Thomas Nield
Thomas Nield is the founder of Nield Consulting Group and an instructor at University of Southern California, where he teaches AI System Safety, developing systematic approaches for identifying AI-related hazards in aviation and ground vehicles. He's authored three books, including Essential Math for Data Science and Getting Started with SQL (both for O'Reilly). He enjoys making technical content relatable and relevant to those unfamiliar or intimidated by it. Thomas teaches classes on data analysis, machine learning, mathematical optimization, and practical artificial intelligence. He’s also the founder and inventor of Yawman Flight, a company that develops universal handheld flight controls for flight simulation and unmanned aerial vehicles.