> For the complete documentation index, see [llms.txt](https://lexica.gitbook.io/lexica/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://lexica.gitbook.io/lexica/getting-started/quickstart.md).

# What is Lexica?

<figure><img src="/files/KRJFHVjthR8xV0SGAmb3" alt=""><figcaption></figcaption></figure>

Lexica is an open-source platform that helps **developers** and **product teams** build robust AI applications powered by LLMs. It offers all the tools for **prompt management and evaluation**.

{% hint style="info" %}
Want to learn about writing content from scratch? Head to the Basics section to learn more.
{% endhint %}

#### With Lexica, you can: <a href="#with-agenta-you-can" id="with-agenta-you-can"></a>

1. Rapidly **experiment** and **compare** prompts on any LLM workflow (chain-of-prompts, Retrieval Augmented Generation (RAG), LLM agents...)
2. Rapidly **create test sets** and **golden datasets** for evaluation
3. **Evaluate** your application with pre-existing or **custom evaluators**
4. **Annotate** and **A/B test** your applications with **human feedback**
5. **Collaborate with product teams** for prompt engineering and evaluation
6. **Deploy your application** in one-click in the UI, through CLI, or through github workflows.

Lexica focuses on increasing the speed of the development cycle of LLM applications by increasing the speed of experimentation.

### How is Lexica different?[​](https://docs.agenta.ai/#how-is-agenta-different) <a href="#how-is-agenta-different" id="how-is-agenta-different"></a>

#### Works with any LLM app workflow[​](https://docs.agenta.ai/#works-with-any-llm-app-workflow) <a href="#works-with-any-llm-app-workflow" id="works-with-any-llm-app-workflow"></a>

Lexica enables prompt engineering and evaluation on any LLM app architecture, such as **Chain of Prompts**, **RAG**, or **LLM agents**. It is compatible with any framework like **Langchain** or **LlamaIndex**, and works with any model provider, such as **OpenAI**, **Cohere**, or **local models**.

Jump here to see how to use your own custom application with Lexica and here to understand more how Lexica works.

#### Enable collaboration between developers and product teams[​](https://docs.agenta.ai/#enable-collaboration-between-developers-and-product-teams) <a href="#enable-collaboration-between-developers-and-product-teams" id="enable-collaboration-between-developers-and-product-teams"></a>

Lexica empowers **non-developers** to iterate on the configuration of any custom LLM application, evaluate it, annotate it, A/B test it, and deploy it, all within the user interface.

By **adding a few lines to your application code**, you can create a prompt playground that allows non-developers to experiment with prompts for your application and use all the tools within Lexica.

###