# Changelog

## 4.0 - 2019-11-29

## 3.0 - 2019-11-25

### Added

* A continuous score for each request to enable ranking of requests in accordance with how bad the model thinks it is. 

### Fixed

* If the amount of data that we are training from is *exactly* 16,000 requests - training will crash and no model will be mounted.
* Some 500 responses were still occasionally returned.

## 2.0 - 2019-11-06

### Fixed

* 500 errors that are returned by the ingestion service.

### Changed

* Explainability has been improved, and is now more readable.

## 1.0 - 2019-10-03

### ​Added

* First distributable cut.

##