In this hands-on workshop, participants will learn how to identify and mitigate bias in NLP models using Python. We'll explore real-world examples from healthcare and education, audit sentiment analysis models for bias, and discuss responsible AI development in an African context. With libraries like transformers, pandas, and scikit-learn, attendees will walk away with practical tools and a new lens for building ethical AI systems that work for everyone. No prior AI ethics experience required — just Python curiosity!