# How UIPath uses Encord

**10x+** dataset growth

As published on [encord.com](https://encord.com/customers/uipath/), April 2026. Captured by usedby on 2026-10-30.

- Company: [UIPath](https://www.usedby.ai/companies/uipath.md)
- Tool: [Encord](https://www.usedby.ai/tools/encord.md)
- Industry: [Artificial Intelligence](https://www.usedby.ai/companies/industry/artificial-intelligence.md)
- Teams: Applied Science

## The use case: how UIPath deploys Encord

UiPath uses Encord to annotate and manage training data across image, video, text, and voice models. It used the platform to expand the training dataset for its table extraction model, with multiple simultaneous annotators and structured review flows.

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

> After using Encord to more than 10x the size of the training dataset, the team achieved more than a 4x reduction in error rate, pushing accuracy above 98% and close to 99%.

- **4x**: “the team achieved more than a 4x reduction in error rate”
- **96–97%**: “Before, the model was performing at around 96–97% mAP on their internal dataset”

> What Encord is bringing to our team now is mostly headspace. Taking away the pain of starting a new project from scratch. We just delegated that away and focused on the model.
>
> Dragos Bobolea, Director, Applied Sciences

Source: [encord.com](https://encord.com/customers/uipath/), captured 2026-10-07.

## Other AI tools used by UIPath

- [Drata](https://www.usedby.ai/tools/drata.md) — Confirmed
- [Dropzone AI](https://www.usedby.ai/tools/dropzone-ai.md) — Confirmed
- [Fireworks AI](https://www.usedby.ai/tools/fireworks-ai.md) — Observed
- [Noma Security](https://www.usedby.ai/tools/noma-security.md) — Observed
- [SeekOut](https://www.usedby.ai/tools/seekout.md) — Observed
- [Synthesia](https://www.usedby.ai/tools/synthesia.md) — Observed

## Encord users in Artificial Intelligence

- [Ambi Robotics](https://www.usedby.ai/companies/ambi-robotics.md) — Confirmed
- [Archetype AI](https://www.usedby.ai/companies/archetype-ai.md) — Confirmed
- [Pickle Robot](https://www.usedby.ai/companies/pickle-robot.md) — Confirmed
- [Standard AI](https://www.usedby.ai/companies/standard-ai.md) — Confirmed
- [Thoro.ai](https://www.usedby.ai/companies/thoro-ai.md) — Confirmed
- [UVeye](https://www.usedby.ai/companies/uveye.md) — Confirmed

## What usedby checked

We compared the story with its live page on 2026-10-30.

- Checked: the figure 10x+ is on the page; its label is our wording.
- Checked: the passage quoted above is copied word for word from the page, near the name of UIPath.
- Checked: the publication date is read from the page’s own metadata, never guessed.
- Checked: UIPath uses Encord. Confirmed line. Latest check across sources: 2026-10-30.
- Not checked: the result itself. We quote it; we did not measure it.

---
Source: https://www.usedby.ai/case-studies/uipath-encord · How we check: https://www.usedby.ai/methodology