> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://humanloop.com/docs/v5/quickstart/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://humanloop.com/docs/_mcp/server.

> Quickstart guides for evaluating and instrumenting your LLM apps.

**If you're technical**, get started by evaluating or logging an AI application
in code:

#### [Eval in code](/docs/quickstart/evals-in-code)

Create an Eval in code

#### [Add logging to your existing app](/docs/quickstart/set-up-logging)

Log your existing app

\


**Or, if you don't want to touch code**, get started by creating a Prompt or an Eval in the UI:

#### [Create a Prompt in the UI](/docs/quickstart/create-prompt)

Create a Prompt in the UI

#### [Agent Eval in the UI](/docs/quickstart/agent-evals-in-ui)

Create an Eval in the UI

> Quickly evaluate your LLM apps and improve them.

## Docs

- [Evals in code](https://humanloop.com/docs/v5/quickstart/evals-in-code.md): Getting up and running with Humanloop is quick and easy. This guide will explain how to set up evaluations on Humanloop and use them to iteratively improve your applications.
- [Agent Evals in the UI](https://humanloop.com/docs/v5/quickstart/agent-evals-in-ui.md): Getting up and running with Humanloop is quick and easy. This guide will explain how to set up evaluations through the Humanloop UI.
- [Create a Prompt in the UI](https://humanloop.com/docs/v5/quickstart/create-prompt.md): This guide will show you how you can use Humanloop to quickly create a new prompt and experiment with it.
- [Set up logging](https://humanloop.com/docs/v5/quickstart/set-up-logging.md): Use Humanloop to add logging to an AI project.