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

# Get Started

An introduction to the Gaffa Browser API. Learn how you can get started building fast, powerful web automations!

Welcome to the Gaffa documentation site! You'll find everything you need here to get started using the API, including [interactive API definitions](/docs/api-reference/post-v1-browser-requests.md), [a comprehensive list of actions](/docs/features/browser-requests/actions.md) you can use to interact with our cloud browsers, and [breakdowns of our example requests](/docs/features/browser-requests/api-playground-examples.md) you can run right away in our API Playground.

{% hint style="info" %}
Gaffa is currently in its very early stages, so we'd love to hear how we can improve our docs and API to make life easier for our users. If you have any questions or comments, please [email us](mailto:support@gaffa.dev) or use [the support tool on our site](https://go.crisp.chat/chat/embed/?website_id=87a5807c-14f5-4ed3-9fbe-3d161610357b).\
\
To stay up to date with the latest developments, features, and news on the mission to support the development of revolutionary AI Agents, sign up for sporadic [newsletter](https://gaffa.dev/#newsletter) updates.
{% endhint %}

{% stepper %}
{% step %}

## Create an account

You can sign up to create a Gaffa account [here](https://gaffa.dev/auth/sign-in). Every new account comes with 500 free credits, which you can use to start building and running automations on the open web right away. You can also use the [API Playground](https://gaffa.dev/dashboard/playground) to explore prebuilt automations built against the Gaffa [demo site](https://demo.gaffa.dev/) and experiment with Gaffa's features.
{% endstep %}

{% step %}

## Making your first browser request

The easiest way to make your first Gaffa [browser request](/docs/features/browser-requests.md) is to use our [API Playground](https://gaffa.dev/dashboard/playground), where you can explore pre-made interactive browser request examples built against our test site. You can run and edit these examples to experiment, or use your 500 free credits to build and test automations on other sites across the open web.

You can also send your first request directly from the command line. Replace `YOUR_API_KEY` with a key from [**Dashboard → API Keys**](https://gaffa.dev/dashboard/api-keys).

```sh
curl --request POST 'https://api.gaffa.dev/v1/browser/requests' \
  --header 'Content-Type: application/json' \
  --header 'X-API-Key: YOUR_API_KEY' \
  --data '{
    "url": "https://demo.gaffa.dev/simulate/table?loadTime=3&rowCount=20",
    "async": false,
    "settings": {
      "actions": [
        {
          "type": "wait",
          "selector": "table"
        },
        {
          "type": "print",
          "size": "A4",
          "margin": 20,
          "orientation": "portrait"
        }
      ]
    }
  }'
```

See [Browser Requests](/docs/features/browser-requests.md) for full cURL, Python, and JavaScript examples.

### Gaffa API Playground examples

Here are all the sample requests we've created for use in the API Playground.

<table data-view="cards"><thead><tr><th></th><th></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><strong>Print to PDF</strong></td><td>Export a web page to PDF and wait for elements to load with the Gaffa API.</td><td><a href="/docs/features/browser-requests/api-playground-examples/export-web-page-to-pdf.md">Export Web Page to PDF</a></td></tr><tr><td><strong>Convert to Markdown</strong></td><td>Export a web page to markdown format - useful feeding into LLM apps.</td><td><a href="/docs/features/browser-requests/api-playground-examples/convert-web-page-to-markdown.md">Convert Web Page to Markdown</a></td></tr><tr><td><strong>Infinitely Scroll</strong></td><td>Scroll the bottom of a page that infinitely loads items and record the interaction.</td><td><a href="/docs/features/browser-requests/api-playground-examples/infinitely-scroll-an-e-commerce-site.md">Infinitely Scroll an E-commerce Site</a></td></tr><tr><td><strong>Capture Screenshot</strong></td><td>Interact with a page and capture the a screenshot of the whole page.</td><td><a href="/docs/features/browser-requests/api-playground-examples/capture-a-full-height-screenshot.md">Capture a Full-Height Screenshot</a></td></tr><tr><td><strong>Form Completion</strong></td><td>Fill out a form in a human-like way and record the interaction</td><td><a href="/docs/features/browser-requests/api-playground-examples/automated-form-filling.md">Automated Form Filling</a></td></tr></tbody></table>
{% endstep %}

{% step %}

## Building your own browser requests

When you're ready to start building your own browser requests, you'll want to explore the available [actions](/docs/features/browser-requests/actions.md), [proxy servers](/docs/features/browser-requests/parameters.md#proxy-servers), [caching](/docs/features/browser-requests/parameters.md#caching) options, and [other endpoints that are part of the Gaffa API](/docs/api-reference/api-reference.md).
{% endstep %}
{% endstepper %}

## <sup>**Want to build faster with AI assistance?**</sup>

Gaffa gives your AI assistant everything it needs to write working code without you explaining the API yourself. Install the [Gaffa AI skills](/docs/ai-tools/tools/gaffa-ai-skills.md) to teach tools like Claude Code, Cursor, Codex, etc. how to write, debug, and test Gaffa requests; they also connect to the [docs MCP server](/docs/ai-tools/tools/gaffa-docs-mcp-server.md) so your assistant can look up actions and parameters as it works. If your tool doesn't support plugins, you can connect the MCP server on its own, or paste the [llms.txt](https://gaffa.dev/docs/llms-full.txt) file into any chat for a quick snapshot of the docs.

{% content-ref url="/spaces/Mlx6Dm0tMl9eKr0tbRvJ/pages/c1c2bf7d7c5c4cdb53233f70a53b30ff0cc71460" %}
[Gaffa AI Skills](/docs/ai-tools/tools/gaffa-ai-skills.md)
{% endcontent-ref %}

{% content-ref url="/spaces/Mlx6Dm0tMl9eKr0tbRvJ/pages/416edc1381c20849bc41111b02e482a722a49b94" %}
[Gaffa Docs MCP Server](/docs/ai-tools/tools/gaffa-docs-mcp-server.md)
{% endcontent-ref %}


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://gaffa.dev/docs/get-started.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.