> For the complete documentation index, see [llms.txt](https://docs.growthfactor.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.growthfactor.ai/guides/changing-site-score-to-evaluators.md).

# Changing Site Score to Evaluators

***

The [GrowthFactor Score](https://docs.growthfactor.ai/data-and-analytics/growthfactor-score.md) is being retired and replaced by [Custom Evaluators](https://docs.growthfactor.ai/data-and-analytics/custom-evaluators.md). You can copy the prompts you wrote for Site Score into an evaluator, so you keep evaluating sites on your own criteria.

This guide maps each part of a Site Score setup to its place in an evaluator, then walks through rebuilding one step by step.

{% hint style="info" %}
Move your **Site Score context** to **Workspace Context** in the **Defaults** tab of [Workspace Settings](https://docs.growthfactor.ai/getting-started/workspace-settings.md#workspace-context).
{% endhint %}

***

## How Site Score Maps to Evaluators

| In Site Score         | In Custom Evaluators                                       |
| --------------------- | ---------------------------------------------------------- |
| A lens                | One evaluator, or one criterion inside a broader evaluator |
| A lens description    | The evaluator's **Instructions**                           |
| Lens weights          | The order you rank criteria in, most important first       |
| A lens's data sources | The evaluator's **Data sources**                           |

***

## Rebuilding Your Score

You need to be a workspace admin to create evaluators.

### 1. Copy what you already have

Open the **Site Score** tab in [Workspace Settings](https://docs.growthfactor.ai/getting-started/workspace-settings.md). Copy each lens description somewhere you can edit them. Note each lens's weight and which data sources it uses.

### 2. Decide how many evaluators you want

You have two options.

* **One broad evaluator.** Combine your lenses into one evaluator that weighs everything. This is the closest match to a single overall score, and the best choice for your workspace default.
* **One evaluator per lens.** Each lens becomes its own narrow evaluator, like a demographics evaluator or a competition evaluator. Use these when you want the breakdown a lens score used to give you.

Many teams do both: one broad evaluator as the default, plus a few narrow ones for a closer look.

### 3. Write the instructions

Start from your lens descriptions. Turn each lens into a criterion, ranked by its weight. Then add what Site Score left implicit: thresholds, dealbreakers, and what each rating means.

For example, a Site Score setup like this:

> **Demographics Fit** (weight 40): How well the population matches our customer.
>
> **Competition Analysis** (weight 30): Density of competitors and complements.
>
> **Foot Traffic** (weight 30): Visitor activity near the site.

becomes instructions like this:

```
Judge how well this location fits a fast-casual restaurant with a
drive-thru. Our best stores sit in suburban trade areas with lots
of family households.

Weigh these, most important first:
1. Demographics. Median household income above $90k is strong.
   Below $60k is a concern.
2. Competition. One or two fast-casual competitors nearby is fine.
   Five or more is saturated. A grocery or big-box anchor nearby is
   a plus.
3. Foot traffic. Steady weekday visits matter most. Ignore late-night
   activity.

```

See [Writing Evaluator Prompts](https://docs.growthfactor.ai/guides/writing-evaluator-prompts.md) for more on thresholds, dealbreakers, and scales.

### 4. Add the same data sources

Add the data sources your lenses used under **Add data source**. Only add the ones your instructions actually use.


---

# 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://docs.growthfactor.ai/guides/changing-site-score-to-evaluators.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.
