Learn to build an autonomous data science agent from scratch using open-source models and modern AI tools. This hands-on workshop will guide you through implementing a ReAct-based agent that can perform end-to-end data analysis tasks, from data cleaning to model training, using natural language reasoning and Python code generation. We'll explore the CodeAct framework, where the agent "thinks" through problems and then generates executable Python code as actions. You'll discover how to safely execute AI-generated code using Together Code Interpreter, creating a modular and maintainable system that can handle complex analytical workflows. Perfect for data scientists, ML engineers, and developers interested in agentic AI, this workshop combines practical implementation with best practices for building reasoning-driven AI assistants. By the end, you'll have a working data science agent and understand the fundamentals of agent architecture design. What you'll learn: ReAct framework implementation Safe code execution in AI systems Agent evaluation and optimization techniques Building transparent, "hackable" AI agents No advanced AI background required, just familiarity with Python and data science concepts.
talk-data.com
Speaker
Zain Hasan
1
talks
Zain Hasan is a Staff AI/ML DevRel Engineer at Together AI. An engineer and data scientist by training, he completed his undergraduate and graduate studies at the University of Toronto, where he worked on artificially intelligent assistive technologies. He founded a company that developed a digital health platform using machine learning to remotely monitor chronically ill patients and later worked as a consultant senior data scientist in Toronto. He is passionate about open-source, education, and community, and has delivered workshops and talks at multiple events and conferences.
Bio from: Small Data SF 2025
Filter by Event / Source
Talks & appearances
Showing 1 of 2 activities