# How to Set Up a LLM Based Personalization Campaign?

## Video Tutorial

{% embed url="<https://youtu.be/Oow7Lc854VY?si=q-kAc9UDbWzGH2IU>" %}

### Step-by-Step Guide:

#### Step 1: Navigate to Personalization

Click **Personalization** in the left-hand navigation bar.

<figure><img src="/files/LtNxwnQgMUtitq9CNFX2" alt="" width="563"><figcaption></figcaption></figure>

#### Step 2: Choose where you are starting from

**Step 2.1: If you are creating a campaign for a new URL**

1. Click **Add New Page**

<figure><img src="/files/Hc6arjXY1zp3h8Pk5GxJ" alt="" width="563"><figcaption></figcaption></figure>

2. Paste your page URL

<figure><img src="/files/D2gLsIYKZIMLQQu2qR1H" alt="" width="563"><figcaption></figcaption></figure>

If your URL redirects, Fibr will automatically update it to the final destination URL. This helps keep your campaigns tied to the right page.

{% hint style="info" %}
The system automatically adjusts the URL to the correct one in case in redirects to a different URL.
{% endhint %}

**Step 2.2: If you are creating a campaign for an existing URL**

1. Find the URL and click **View Campaigns**

<figure><img src="/files/gI5P1zePwu5qPD3RQ0pD" alt="" width="563"><figcaption></figcaption></figure>

2. Click "**Create Campaign"**

<figure><img src="/files/Rg4vWWrXSlNKmQiRSEO8" alt="" width="563"><figcaption></figcaption></figure>

#### Step 3: Select Ad Personalization

Choose **Ad Personalization** from the list of personalization types.

#### Step 4: Add Campaign Details

Give your campaign a descriptive name and connect Google Analytics to get better, data-driven recommendations.

<figure><img src="/files/yaHVGKXyfklRJxpxlwbG" alt="" width="563"><figcaption></figcaption></figure>

{% hint style="success" %}
**We Recommend Connecting Google Analytics (GA4)**

Toggle on "Connect Google Analytics" to unlock more accurate personalization suggestions. When connected, Fibr will:

* Analyze real user behavior (scroll depth, time on page, bounce rate, and more)
* Use audience insights to make recommendations that match your actual traffic patterns
  {% endhint %}

#### Step 5: Add a segment

Click **Add Segment** to start defining the LLM Platforms you want to personalize for.

<figure><img src="/files/apChrq6zQJCUF7Evd5Uc" alt="" width="563"><figcaption></figcaption></figure>

***

#### Step 6: Define your LLM Platform segments

Choose the LLM segments you want to create personalized experiences for.

<figure><img src="/files/ivR5ifxeT8lj40DRjZye" alt="" width="563"><figcaption></figcaption></figure>

Once you are done, click **Continue** to generate recommendations.

Tip: Start with a few high-impact locations first. You can always add more segments later.

***

#### Step 7: Review AI suggestions

Fibr generates suggestions to personalize your web experiences for the LLM Platform segments you defined.

Review the recommendations from Fibr AI.

<figure><img src="/files/koKGQkjiS2z9dloOOt7o" alt="" width="563"><figcaption></figcaption></figure>

If you prefer to choose elements yourself, click **Personalize Manually**.

<figure><img src="/files/KjXbYy9EfOq4FIyXo5U2" alt="" width="563"><figcaption></figcaption></figure>

You are in control here. AI is simply helping you move faster.

#### Step 8: Create the campaign and generate variants

Click **Create Campaign** to generate variants.

#### Step 9: Set measurement and holdout

1. Add a **success metric** to track conversions
2. Set a **holdout** percentage to decide how many visitors should still see the original experience

{% hint style="info" %}
By default the holdout is 10% and the minimum suggested holdout is 5%.&#x20;

This keeps your results reliable while you personalize.
{% endhint %}

#### Step 10: Publish or schedule

Click **Publish** to go live now, or **Schedule** to launch later.

Once live, visitors from your defined location segments will see their tailored experience instead of the original.

You are ready to launch.


---

# Agent Instructions: 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:

```
GET https://support.fibr.ai/fibr-personalization-suite/llm-based-personalization/how-to-set-up-a-llm-based-personalization-campaign.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.
