# How Gamma uses Patronus AI

**1K+ hours**: “1K+ hours saved on manual evaluation per month through Patronus Judges”

As published on [patronus.ai](https://www.patronus.ai/case-studies/gamma-scaling-ai-performance-with-automated-evals-and-rigorous-experimentation). Captured by usedby on 2026-10-06.

- Company: [Gamma](https://www.usedby.ai/companies/gamma.md)
- Tool: [Patronus AI](https://www.usedby.ai/tools/patronus-ai.md)
- Teams: AI team

## What the story says

Gamma's AI team uses Patronus Judges to automatically detect missing-content errors in generated slide decks, and Patronus Experiments to benchmark LLMs and distill a large set of user feedback samples into a smaller ground truth dataset.

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

> Gamma’s task of slide deck generation resulted in long, open-ended outputs that were expensive to inspect manually and annotate. Patronus Judges excel for this challenge, where teams require a heuristic to grade thousands of samples.

- **15+**: “15+ LLMs benchmarked with Patronus Experiments”
- **10K+**: “10K+ real world samples distilled into one coherent ground truth dataset”

> Patronus helped our AI team find signals and patterns of error in our datasets. Their LLM Judges enabled us to triage errors and optimize our AI outputs in production settings. Patronus up-leveled our evaluation process and was an invaluable part of our workflow.
>
> Jon Noronha, Co-Founder of Gamma

## What usedby checked

We compared the story with its live page on 2026-10-06.

- Checked: the figure 1K+ hours is printed word for word on the page, near the name of Gamma.
- Checked: the passage quoted above is copied word for word from the page, near the name of Gamma.
- Checked: Gamma uses Patronus AI. Confirmed line. Latest check across sources: 2026-10-06.
- Not checked: the result itself. We quote it; we did not measure it.

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