> For the complete documentation index, see [llms.txt](https://docs.hackle.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.hackle.io/en/ab-test/about/ab-test-one-pager.md).

# Writing an A/B Test Planning Document

{% hint style="info" %}
When designing an A/B Test, try using this One-Pager template.

It helps you plan and prepare more thoroughly and extract valuable lessons learned.
{% endhint %}

{% stepper %}
{% step %}

### Experiment Preparation

Before starting the experiment, lay out the problem and the hypothesis as a single flow.

* **Problem:** Describe the problem users are running into in one sentence.
* **Supporting data:** Collect the qualitative and quantitative data that backs up the problem.
* **Hypothesis:** Describe what you will change and what result you expect.
* **Duration:** Set how long the experiment will run.
* **User distribution timing:** Define when users are distributed into the variations.

{% hint style="info" %}
**Example**

* Problem: Product list views are high, but the product click-through rate is low.
* Hypothesis: Displaying the discount rate on the product list will increase the click-through rate.
* Duration: Approximately 2 weeks
* User distribution timing: When a user views the product list
  {% endhint %}
  {% endstep %}

{% step %}

### Experiment Execution

Define the variations and how you will measure them.

* **Changes:** Describe the experience applied to Group A and Group B.
* **Experiment target:** Define which users are included in the experiment.
* **Success Metric:** Choose the key metric that determines whether the experiment succeeded.
* **Supporting metrics (optional):** Add metrics to monitor alongside the key metric.
* **Guardrail Metrics (optional):** Choose the metrics that must be maintained during the experiment.
* **Experiment URL (optional):** Add the URL where the experiment can be verified.

{% hint style="info" %}
**Example**

* Changes: Group A keeps the current experience, and Group B gets the change applied.
* Experiment target: All users
* Success Metric: Product click-through rate — `click_product / view_product_list`
* Supporting metrics: Add-to-cart rate, purchase conversion rate
* Guardrail Metrics: Order cancellation rate, Retention
  {% endhint %}
  {% endstep %}

{% step %}

### Post-Experiment

Interpret the results and connect them to your next hypothesis.

* **Result summary:** Record the winning group and how the key metric changed.
* **Result interpretation (optional):** Summarize whether the results support your hypothesis.
* **Next hypothesis (optional):** Write a follow-up hypothesis based on what you learned.

{% hint style="info" %}
**Example**

* Result summary: Winner group: Group B
* Result interpretation: If the click-through rate increased for users who saw the discount rate, they are likely highly price-sensitive.
* Next hypothesis: If users are price-sensitive, should we offer sorting by discount rate?
  {% endhint %}
  {% endstep %}
  {% endstepper %}


---

# 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://docs.hackle.io/en/ab-test/about/ab-test-one-pager.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.