Support

This article provides more in-depth information on the Autocoding Mode Guardrail.

Introduction

Each verbatim in codeit can contain several codes, for example "I liked the service but the price was too expensive". To handle this use case, it is important to understand how the AI will apply code for a multi-coded verbatim.
This is controlled by the "Autocoding Mode" guardrail.

The guardrails are available at project-level and at task-level.

There are 2 options for the Autocoding Mode

Auto Coding Mode Explanation

Minimise Coding Gaps

The aim of the "Minimise Coding Gaps" mode is ensure that the AI can only apply suggestions from the machine learning if the verbatim is completely coded. To understand this, consider the following example:

Suppose that the codeit AI is presented with the verbatim:
"They give good service, but it was expensive and the staff were rude"

Suppose also that the Machine Learning generates the following suggestions, in response:

In this example, the AI has only suggested 2 codes (Code 3 and Code 7), and the texts suggested does not cover the whole verbatim.
Therefore, it is likely there is a gap in the coding. In this sense the codes applied are not considered "complete" and the AI has missed a code - i.e. 'the staff were rude'.  Using "Minimise Coding Gaps", in this case, would result in none of these suggestions being applied.

So, you would use "Minimise Coding Gaps" mode if you want to be as sure as possible that applying the Machine Learning suggestions will result in completely coded items with no gaps of this sort. Note, that this sets quite a high bar for the AI and will result in higher "completeness" of autocoding at the expense of a lower number of items autocoded overall.

Maximise Coding Volume

The "Maximise Coding Volume" mode offers an alternative approach - we allow the Machine Learning Layer to autocode any suggestions that meet the minimum "Autocoding Threshold". This increases the possibility of gaps in the coding, but hugely increases the volume of codes that the AI is able to apply from the Machine Learning. 

In the example above, for verbatim "They give good service, but it was expensive and the staff were rude" , the 2 suggested codes would be applied by the AI when using this mode, resulting in a higher autocoding volume but a missing code.

You would use "Maximise Coding Volume" to get a high volume of autocoding. It is likely that some codes will be missed though so it might not result in the quality needed.

The codeit AI will use the Coverage threshold to calculate how much the verbatim should be "covered" to be considered as completely coded by the AI.

See more details about the coverage threshold here.