Towards Data Science is a community-powered publication that showcases work in data science, machine learning and artificial intelligence. Every day newcomers, seasoned researchers and industry practitioners publish tutorials, research notes and real-world case studies that help the field move forward.

Towards Data Science

A comprehensive guide to building a multi-agent SQL assistant using CrewAI and Streamlit. The system features three specialized agents: a query generator that converts natural language to SQL, a reviewer that optimizes queries, and a compliance checker that ensures data safety. Key features include human-in-the-loop checkpoints for user control, real-time LLM cost tracking, and safety measures to prevent PII exposure. The tutorial covers agent architecture, task definitions using YAML configurations, database schema integration, and a complete Streamlit interface implementation with practical examples and cost analysis.

A Multi-Agent SQL Assistant You Can Trust with Human-in-Loop Checkpoint & LLM Cost Control