> For the complete documentation index, see [llms.txt](https://nationgraph.gitbook.io/nationgraph/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://nationgraph.gitbook.io/nationgraph/help-center/readme/automations-overview/ranked-automations.md).

# Ranked Automations

Build a prioritized target list using configurable scoring.

Ranked automations help you decide who to contact first.

This matters when your feed has **2,000+ signals**.

Sorting by data type, account type, or template does not show intent clearly enough.

Use ranked automations when you want a prioritized list instead of a flat feed.

Click here to watch [video](https://screen.studio/share/uRtcMGhq).

{% embed url="<https://screen.studio/share/uRtcMGhq>" %}
Ranking your opportunities
{% endembed %}

### Create a ranked automation

{% stepper %}
{% step %}

#### Start the automation

Go to **Automations → New Automation → Rank Your Opportunities**.

You can pull in signals from one template or from all templates.
{% endstep %}

{% step %}

#### Choose the signal set

Filter the run by data type when needed.

For example, you can rank only **meeting minutes** and **YouTube** signals.
{% endstep %}

{% step %}

#### Configure the scoring levers

Set the ranking weights that matter to your team.

You can weight each lever or turn them off and let the AI prioritize the list.
{% endstep %}

{% step %}

#### Name and run it

Name the automation and create it.

You do not need to lock the run to a single template.
{% endstep %}
{% endstepper %}

### What ranked automations use

Scoring can include:

* **NationGraph Signal Score**
* **Population**
* **Recency**
* **Signal count**
* the weighting logic you configure for the run

{% hint style="info" %}
Ranked automations now run daily. This keeps the list fresh without manual reruns.
{% endhint %}

### Use NationGraph Signal Score

The **NationGraph Signal Score** helps the AI rank institutions using your company documentation and the matching signals.

Use it when you want to:

* sort the highest-intent accounts to the top
* compare institutions inside the same territory
* decide what to work, sync, or export first

Other scoring levers let you prioritize:

* larger institutions through **Population**
* newer activity through **Recency**
* denser activity through **Signal count**

### What shows in ranked results

Each institution receives a score.

Results update daily, so ranks shift as new signals arrive.

You can filter the table by:

* template
* data source
* state

Click into an institution to review the signals and signal count behind the rank.

Use the results to action emails or read the underlying signals.


---

# 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://nationgraph.gitbook.io/nationgraph/help-center/readme/automations-overview/ranked-automations.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.