# Promptfoo

- **Website:** <https://promptfoo.dev>
- **Primary alias:** `promptfoo.dev`

## Description

Promptfoo is a brand that specializes in evaluating and testing the quality of LLM prompts. LLM stands for Language Model, and with promptfoo, you can ensure high-quality outputs by testing your prompts. 

The process is simple: start by creating a list of test cases using a representative sample of user inputs. This helps reduce subjectivity when tuning prompts. Next, set up evaluation metrics. You can choose from the built-in metrics, LLM-graded evals, or define your own custom metrics. 

Once you have your test cases and evaluation metrics in place, promptfoo allows you to compare different prompts and model outputs side-by-side. This allows you to select the best prompt and model for your specific needs. You can also integrate the promptfoo library into your existing test or CI workflow.

With promptfoo, you can ensure the prompt quality and accuracy of your LLM outputs effortlessly. Join over 10 million users who rely on promptfoo for their LLM apps. Visit the promptfoo website today to get started.

## Industries

- 🖥 Computers Electronics and Technology
- 🖥 Artificial Intelligence and Machine Learning _(under Computers Electronics and Technology)_
- 🖥 Programming and Developer Software _(under Computers Electronics and Technology)_

## Links

- [github](https://github.com/promptfoo)
- [linkedin](https://linkedin.com/company/promptfoo)

## Logos & icons

- logo _(primary)_ — PNG, SVG — [download](https://cdn.brandfetch.io/idJ78V-1Fs/w/820/h/820/theme/dark/logo.png?c=1bxid64Mup7aczewSAYMX&t=1787815220484)
- icon _(primary)_ — JPEG — [download](https://cdn.brandfetch.io/idJ78V-1Fs/w/400/h/400/theme/dark/icon.jpeg?c=1bxid64Mup7aczewSAYMX&t=1787815220588)

## Colors

| Name | Hex | Theme |
| --- | --- | --- |
| Scarlet | #fe2c06 | accent |
| Shark | #1c1e21 | dark |
| White | #ffffff | light |

## Fonts

- var(--ifm-font-family-base) — asset _(custom)_

---

_Source: <https://brandfetch.com/promptfoo.dev>_
_See [/llms.txt](/llms.txt) for a full list of agent-readable pages, and [/auth.md](/auth.md) for how agents authenticate._