> For the complete documentation index, see [llms.txt](https://keak.gitbook.io/keak-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://keak.gitbook.io/keak-docs/basics/editor/starting-the-a-b-test-and-setting-a-conversion-goal.md).

# Starting the A/B Test & Setting a Conversion Goal

Once you have a variation prepared, **launching the A/B test is done in one click.** In the Keak sidebar, choose the variation you want to test first and click the **“Test”** button next to it​

After clicking “Test,” Keak will prompt you to **define your conversion goal for this test**. This step tells Keak what constitutes a “win” so it can determine which variation performs the best. You’ll typically see two fields:

* **Page URL:** The URL of the page that represents a successful conversion. Often, this is a “thank you” or confirmation page that users reach after completing a desired action (purchase, signup, etc.)​. For example, if you’re optimizing a sign-up page, you might enter the URL of the “Thank You” page shown after a user submits the form. Every time visitors in the test reach this URL, Keak counts a conversion for the variation they saw.
* **Page Name (Event Name):** A name for the conversion event you are tracking. This could be something like "Purchase", "Lead", "Sign-Up", or any label that makes sense for your goal. The name is just for your reference in reports; it doesn’t affect functionality. 

Enter the appropriate URL and a name for the conversion event. Keak will start monitoring visits to that URL as the key success metric for this test.  

{% hint style="info" %}
*Note: If your conversion isn’t tied to a page load – say it's a button click or form submission on the same page – you can set up a custom event to track that. See the* [*custom event tracking section*](/keak-docs/basics/markdown/tracking-custom-events-button-clicks-form-submissions-etc..md)*.*
{% endhint %}

Now you’re all set -hit **“Start Test”**. Keak will activate the A/B test on your site, and live visitors will begin to see either the original content or the new variation, distributed randomly. From this point on, Keak handles the rest: it will track how many visitors convert (reach the goal URL or trigger the event) under each version and use that data to decide a winner.

While the test is running, you can monitor its progress in your Keak dashboard. The dashboard will show metrics like impressions (views) and conversions for each version, along with a calculated **conversion rate** and a confidence level indicating if one variation is outperforming the other significantly. Keak recalculates the statistics continuously with each new visitor, and it will automatically stop the test as soon as the results meet the significance criteria you set (more on that in [**Understanding Significance**](/keak-docs/basics/images-and-media.md)). You can also manually pause or end the test anytime from the dashboard if needed.


---

# 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 dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://keak.gitbook.io/keak-docs/basics/editor/starting-the-a-b-test-and-setting-a-conversion-goal.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.