When Prompting Beats Training: Agentic Labeling for Specialized Visual Data - November 9, 2026

Name: When Prompting Beats Training: Agentic Labeling for Specialized Visual Data - November 9, 2026
Start: 2026-11-09
End: 2026-11-09

Nov 09, 2026

9:00 AM - 10:00 AM PST

Online. Register for the Zoom!

Daniel Gural

Head of Physical AI Partnerships, Voxel51

About this event

Frontier multimodal models handle familiar concepts well and struggle on niche ones: sorting drill-core samples into 35 geological classes, or telling adhesion from scarring on a ceramic substrate. Jacob Sela's study across 11 specialized visual datasets in manufacturing inspection, geology, and medical imaging found that a few labeled examples in the prompt can close much of that gap, and it also found where that stops working.

This workshop is about applying those results to your own labeling work. We start from what the study measured, then build a few-shot labeling task live with Agentic Labeling in Voxel51 on a real inspection dataset, and use the data to decide when to keep prompting and when to train a specialist model.

Host

What you’ll learn:

Niche versus hard: how in-context examples supply domain knowledge a model is missing, and how to tell a niche task from a genuinely hard one
What the study measured: on an industrial defect task, one labeled example per class raised macro-F1 from 34% to 59% with no fine-tuning, while on other tasks trained specialists pulled ahead at 5 to 10 examples per class
Building a few-shot labeling task: define classes, pick reference examples, preview predictions on a small batch, and refine the instructions
Finding the crossover point: when to stop prompting a foundation model and train a specialist on bootstrapped labels
Running it on your own data: attendees get free GPU compute from Nebius to try the workflow after the session

Who this is for:

Machine learning engineers and data scientists working on specialized visual data
Annotation leads deciding between prompting foundation models and training specialists
Teams in manufacturing inspection, robotics, agriculture, or medical imaging
Anyone labeling concepts that public datasets do not cover