> ## Documentation Index
> Fetch the complete documentation index at: https://docs.jabrod.com/llms.txt
> Use this file to discover all available pages before exploring further.

# The at-risk report

> Read the list, check the model, and export it.

The report is the last step of a workspace. It appears once a model has been trained.

## Customers at risk this week

Each row is one active customer, highest risk first:

| Column | Meaning |
| - | - |
| Customer | Name, plan and monthly revenue where you uploaded them, or the customer id |
| Risk | The chance of churning within your prediction window, as a percentage, with a bar |
| Reasons | The things raising this customer's risk most, from [the model's templates](https://docs.jabrod.com/signals/model.md#reasons) |

Show the **Top 25**, **Top 50** or **All**, and use **Find a customer** to search by name or id. A customer with nothing pushing their risk up shows "No single strong reason".

## How good is this model

Next to the list, the model's results on the most recent weeks, which it never saw while training:

* **AUC on unseen weeks**, with a verdict: good, fair, weak, not enough history, or too good to be true. See [quality numbers](https://docs.jabrod.com/signals/model.md#quality-numbers).
* **Top 10% flagged** and **Top 50 flagged**: of the customers ranked highest, how many really left within the window.
* **Learned from**: how many customers, how many of them left, over how many days.
* **Tested on**: the customer-weeks and dates the numbers come from, and the date training stopped.

Read this before acting on the list. A weak model means more history or usage data would help.

## What drives risk here

The features that mattered most to this workspace's model, across all customers.

## Export and retrain

* **Export CSV** downloads the whole list with every column.
* **Retrain** trains the model again on the data in the workspace.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.