This quickstart guide is designed to help you get an autoreplies with articles configuration up and running with your existing help center content.
Autoreplies with articles are automated responses to a support request sent through an email or web form. Email autoreplies with articles suggest up to three help center or knowledge base articles in the email response to help a customer resolve their issue. Web form autoreplies with articles immediately respond to a customer's support request through a web form with up to three links to potentially relevant knowledge base articles.
To get the most out of autoreplies with articles, your help center should have at least 10 articles that cover commonly-asked questions.
This article contains the following steps:
Step 1: Evaluate your current help center content
Take a look at the content offered in your help center. You can optimize your help center content for autoreplies with articles with some small changes.
In particular, look at the following article elements:
- Titles: Try to title your articles using language and phrasing your customer might use in a search, or in a ticket description. Simple questions ("How do I reset my password?") or phrases ("Resetting a password") are a good approach.
- Introductions: The first 75 words of an article are weighed most heavily when being assessed, so getting relevant keywords in your introduction is key. Try to start your articles with clear, focused paragraphs.
- Topics: Create bite-sized articles that address single, narrowly-focused topics, rather than long articles with multiple separate, if related, sections. For example, instead of writing one article including all profile-related settings, break that information up into separate articles for each setting. You can connect these smaller articles together using a related articles list, or collect them in a resource article containing links to all profile-related articles.
Keep in mind that these are just suggestions for building a help center that will work with autoreplies with articles. You can apply any, all, or none of them to your help center content at any time during the trial.
Related articles:
Step 2: Activate autoreplies with articles
Next, you can activate autoreplies with articles. Where you add it depends entirely on your Zendesk products and integrations, and where you think it will best fit into your setup. You can use it to offer autoreplies with articles through email notifications or web forms, in the Web Widget (Classic) or the mobile Support app, and in conjunction with the Slack integration with Zendesk.
Related articles:
Step 3: Assess performance
With a few simple configurations, you can evaluate how autoreplies with articles impact your customer interactions. Creating ticket views, as well as using your Explore dashboards, can help you decide if it is the right tool for you.
Creating views for autoreply tickets
You can create views for tickets affected by autoreplies, to easily see how your end users are interacting with the suggested articles, and to assess whether it is working for you.
You’ll want to use triggers and tags to identify impacted tickets and sort them into autoreply-only views. Your basic autoreply views can include (but are not limited to):
- Tickets autoreplies with articles have fired on
- Tickets autoreplies with articles have helped customers self-solve
- Tickets autoreplies with articles have fired on but not solved
Related article:
Analyzing autoreply activity
Autoreplies with articles have a dedicated dashboard in Explore that monitors metrics for your autoreplies with article recommendations and bot builder activity.
- Autoreplies for article recommendations, including suggestion rate, click-through rate, resolution rate, and rejection rate.
- Bot builder activity for messaging, including metrics for total users, engaged with bot, and transferred to agent.
Usage data is gathered immediately upon implementation. You can begin monitoring performance through your Explore dashboard right away, or wait until more information is available. Commonly, users check data after 24 hours, 48 hours, one week, and three weeks to see how performance performance changes over time.
Related articles: