Best practices: Optimizing for autoreplies with articles

What's my plan?

Suite

Team, Growth, Professional, Enterprise, or Enterprise Plus

This functionality is part of AI agents. Usage is measured by automated resolutions.

When you’re starting out with a AI agents, it can be difficult to know how to prepare for and use the feature in the best way possible. In this article, we’ve included four things you can do when implementing your bot to set you up for success.

This article contains the following sections:

• Writing the right articles
• Using customer segments and article labels together
• Checking your placeholders
• Monitoring early performance

Writing the right articles

In many cases, we find that customers haven’t done enough prep work before they start using a bot. One key step you can take is to audit your recent tickets -- maybe from the previous week -- to find tickets where customers really could have self-solved their problem.

For instance:

• Review tickets where a macro was used to solve the problem in one touch. Could there be an article for this? Go write that article.
• Review common tickets that were just answered in one touch: Could there be an article for those that would have allowed customers to self-solve? Go write that article.

See Optimizing your articles for autoreplies.

Using customer segments and article labels together

The power of article labels really becomes evident in a situation where you can segment your customers during ticket creation. Here’s a scenario:

You’re a game developer supporting iOS and Android platforms. You have two channels for incoming tickets: one for iOS issues and one for Android. Using trigger conditions, you can create two autoreply triggers, one for each channel. Then you can use article labels to serve up only iOS or Android articles where they make sense.

Your customers may be more varied than that, so stop for a second and really think about how you can best segment them, and create useful conditions around them. Then, you can serve them the best articles possible.

See Best practices: Using labels for autoreply triggers.

Checking your placeholders

There are specific placeholders to use in the email notification body of your autoreply triggers. They determine how suggested articles are displayed in the responses sent to your end users.

Make sure you set them up properly using the placeholders {{autoreply.article_list}}and {{autoreply.first_article_body}}:

See Configuring email autoreplies.

Monitoring early performance

We’ve built all the key data points into Insights to allow you to really monitor, report, and slice away at your tickets and their deflection data. There is so much you can learn if you spend the time building a few reports (or just digging into the default ones).

About 48 hours after you begin using autoreplies, you can start monitoring performance in the prebuilt dashboard.

See Analyzing your autoreplies.