Alex Rainey

Pedro is indeed right in terms of how that needs to be setup. Which unfortunately is a bit cumbersome and time-consuming. Especially as you're not going to be able to capture all the ‘small talk’ phrases to respond to.

Another alternative, albeit a bigger change, is to use something like My AskAI (Zendesk marketplace) to replace Zendesk's AI with something else. We can handle small talk without any additional setup from yourselves, and your AI agent can deflect ~70% of support tickets once it's been trained on your help docs.

Check out the marketplace listing to find out more, or happy to answer any other questions you have here.

We're using AI to help reply to users and generate draft replies for our agents. We're an AI customer support Zendesk marketplace app (that we built ourselves) for our agents.

It's saving everyone a few hours a week and currently deflecting 70%+ of our support tickets. Which is great as it frees up agents for the more complex tickets.

I'm seeing more and more companies adopt AI in customer support, which is super exciting!

Hey all,

We have an AI customer support app in the Zendesk marketplace.

One of the features of this app is to insert an answer drafted by AI (using knowledge from your help docs) into the editor.

The code we're using is:

client.invoke("ticket.editor.insert", answer);

My understanding is that HTML can be passed into this, which is fine and working for links, bold, italics, etc.

But, I can't find any way to pass in a line break e.g.


Has anyone else come across this or managed to solve this?

We've developed an AI agent (bot) for Zendesk that's available on the marketplace: https://www.zendesk.co.uk/marketplace/apps/messaging/139/my-askai/

One of our core goals is to bring hallucinations down to virtually zero. You train your AI agent on your help docs, and it will only answer questions from content within those help docs. The AI will say when it can't answer a question or if something is off topic.

Over the last month, we've handled 30,000+ conversations, with over 75% of them being resolved by our AI agent.

Hope this helps! I know first hand how a few hallucinations can make a business really weary about implementing AI in customer support.