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 practical guide to implementing human-in-the-loop (HITL) agentic workflows using LangGraph. Covers the core mechanics of interrupts and checkpointing, with a concrete example: a social media content generation pipeline that posts to Bluesky. Explains how to place interrupts at both node and tool levels, manage state persistence with SQLite checkpointers, use thread IDs to resume paused workflows, and shares best practices for avoiding common interrupt pitfalls like non-deterministic re-execution.

Building Human-In-The-Loop Agentic Workflows