Table of content
How it works
AI call scoring allows you to verify at scale how well your Sales representatives perform against your methodology and to identify the most relevant coaching opportunities to boost your team’s performance.
Once your AI call scoring templates are set up, Modjo AI will analyze all the calls matching your templates criteria (based on the filters you used) and score each call based on the questions of the template.
Finding coaching opportunities at scale
To see the AI call scoring results at scale, go to the Analytics section and select the AI call scores tab.
In this tab you will find the average AI call score of each of your template and of each of your team members.
You can use the filters on the left to refine your search.
Then if you want to see the performance for a specific template all you have to do is click on it and the interface will adapt dynamically to show you the score for each template question and show you calls for this specific template.
💡 This is the best entry point to identify coaching opportunities at scale! If we look at the example in the screenshots for instance: the template with the lowest score is “Inbound 1st call - BANT” and then the questions where the team most needs to improve are “timeline”, “budget” and “authority”. As a manager, you can then organize dedicated coaching sessions on these topics that all your teams will benefit from.
Finally, you may want to find coaching opportunities for a specific team member. To do so, you can filter select your team member in the “team members” insert of the analytics and analyze on which templates and template questions, your team member most needs coaching.
Check the AI call score for a specific call
To check the AI call score for a specific call, go and check this call details page and click on the activity tab or click directly on the score that appears at the top left of your video player.
In the activities tab, to see the details of the score, click on the “show details” button.
There you will see for each question of your template the AI assessment of whether it was properly done during the call or not along with:
A summary of how the AI justifies the assessment
Timestamps to listen to the moment of the call where the AI found the justification
The AI can assess the call with 4 answers:
True: if the answer to the template question is true
False: if the answer to the template question is false
Partial: if the AI assesses that the Sales representative actually did what was asked in the question but could have gone further. It usually happens for more complex questions.
Not applicable: if the topic was mentioned during the call but not necessarily as framed in the AI call scoring question. For example, if the question is “Has the Sales Rep asked the propsect budget?” and that the Sales hasn’t done it but this is because the prospect proactively started talking about the budget then the model will send a not applicable value. The not applicable value is neutral in the scoring (it won’t be taken into account in the computation of the AI call scoring)
You also have the possibility to assess whether you agree with the AI assessment from the call details page:
Use
👍 Agreewhen:The AI correctly validated the question and it was well-mentioned in the call, with a sensible justification.
The AI correctly identified a lack of mention in the call.
Use
👎 Disagreewhen:The AI correctly validated, but the justification is un-related to the question.
The AI incorrectly validated, and the element was not mentioned in the conversation.
The AI incorrectly claimed no mention, while it was mentioned in the call.
You will then find an accuracy score within your template setup and will be able to identify where you might want to review and improve your prompt to improve accuracy.
We consider that an accuracy of 70-80% is a good start to be able to deploy the template with interpretable results.