Inspect Fill Levels with Vision AI

​On a high-speed bottling line, even small under-fills can mean lost product, customer complaints, and missed quality targets. Building a computer vision inspection workflow to catch them has traditionally meant picking models, wiring up workflow steps, and writing glue code before you see a single prediction.

​In this live session, Roboflow Full Stack Engineer Roger Garcia will demonstrate how to build a bottle fill level inspection workflow from scratch using the agent in Roboflow. Roger will walk through how one can stand up the entire pipeline, with RF-DETR detecting bottles and a custom model trained in Roboflow Rapid measuring fill levels.

​You will see how the agent picks the right models, configures the workflow steps, and trains a custom fill level model for you, all from a chat interface. By the end of the session, you'll have a clear blueprint for translating an inspection idea into a working pipeline, whether you're working on beverage filling, pharmaceutical capping, or another high-speed quality control task.

​--

​Every week we dive into the world of computer vision and explore new tools, interesting projects, and tutorials. This webinar is open to everyone, we hope to see you there!

​We'll also make time at the end for open Q&A.