Recent searches


No recent searches

Is there any way to customize Agent Messages metric in Messaging Tickest

Answered


Posted Nov 14, 2023

Good morning everyone, I'm trying to solve an issue related to the analysis of tickets created via WhatsApp using the messaging dataset. Specifically, I need to understand how many messages/comments were provided by Agents to tickets created using WhatsApp.

I have two alternatives: using the Update Histories dataset where the "agent comment" metric does not correspond to the actual WhatsApp conversation, or using the Messaging dataset where the "agent messages" metric counts the actual messages exchanged with a customer but also count messages from automated agents we have activated to overcome the 24-hour validity limit of WhatsApp messages.

In a few words, I would like to filter out agent comments generated by bots, but it doesn't seem possible to create custom metrics for agent comments using Messages Dataset.

Any ideas for a workaround or did you have any similar issues ? 

Thanks a lot for your help


2

1

1 comment

image avatar

Dakota

Zendesk Luminary

Here are a few options to help filter out the bot messages when analyzing agent messages in the Messaging Tickets dataset:

  1. Use the "Assignee ID" field to differentiate bot agents vs human agents. You can create a metric like "Assigned Human Agent Messages" filtered to tickets where:
Assignee Type = 'Agent'
AND
Assignee ID != <bot 1 ID> 
AND 
Assignee ID != <bot 2 ID>

This will only count messages by human agents.

  1. Create a custom tag or field at the ticket level to denote "Bot Assisted" tickets. Then filter these out.
  2. Use the Ticket Audits dataset and look at changes to the "Assignee ID" field. Where it flips to a bot and back to a human, you can selectively count messages before and after.
  3. Use Zendesk API to pull all messages and programmatically filter out ones from known bot IDs based on the "author_id" in the message.

Hope this helps!

0


Please sign in to leave a comment.

Didn't find what you're looking for?

New post