# How SharperShape uses Labelbox

**50%**: “cut average cost to create the training data by as much as 50%”

As published on [labelbox.com](https://labelbox.com/customers/sharper-shape-customer-story/). Captured by usedby on 2026-10-07.

- Company: [SharperShape](https://www.usedby.ai/companies/sharpershape.md)
- Tool: [Labelbox](https://www.usedby.ai/tools/labelbox.md)
- Teams: Data Science / AI

## What the story says

Sharper Shape uses Labelbox to create labeled training data for computer vision models that detect utility hazards in drone imagery of power infrastructure. Internal and external contributors annotate together, and the team imports its model into Labelbox for a model-assisted review loop.

Summary written by usedby from the source page, in English. The figures are those of Labelbox and SharperShape, not ours.

> Sharper Shape cut average cost to create the training data by as much as 50% while maintaining the highest-quality signal, and sped up model training by over 10X — freeing the team to focus on model building and deployment.

- **10X**: “sped up model training by over 10X”

> Before using Labelbox, we struggled with managing our training data creation infrastructure and manual experiment tracking.
>
> Jaro Uljanovs, Data Science / AI at Sharper Shape

## What usedby checked

We compared the story with its live page on 2026-10-07.

- Checked: the figure 50% is printed word for word on the page, near the name of SharperShape.
- Checked: the passage quoted above is copied word for word from the page, near the name of SharperShape.
- Checked: SharperShape uses Labelbox. Confirmed line. Latest check across sources: 2026-10-07.
- Not checked: the result itself. We quote it; we did not measure it.

---
Source: https://www.usedby.ai/case-studies/sharper-shape-labelbox · How we check: https://www.usedby.ai/methodology