Recent searches
No recent searches

Jeremy Korman
Joined Apr 14, 2021
·
Last activity Jan 30, 2025
Following
0
Followers
0
Total activity
28
Votes
7
Subscriptions
4
ACTIVITY OVERVIEW
BADGES
ARTICLES
POSTS
COMMUNITY COMMENTS
ARTICLE COMMENTS
ACTIVITY OVERVIEW
Latest activity by Jeremy Korman
Jeremy Korman created a post,
Hello Zendesk Users,
We're excited to highlight brand new capabilities that we've recently released. In this edition, we have 5 demo videos covering:
- Copilot similar tickets: Help agents find similar tickets faster
- Department spaces: Segment access to tickets by brand or department
- Performance overview dashboard for AI agents
- AI agents for voice: Automate voice support (Powered by PolyAI)
- Simultaneous chats for customers: Multi-conversation messaging
Check out all the videos on the YouTube playlist to see these capabilities in action 📹 🤓
Posted Jan 30, 2025 · Jeremy Korman
0
Followers
0
Votes
0
Comments
Jeremy Korman created a post,
Hello Zendesk Users,
We're excited to highlight brand new capabilities that we announced as part of our AI Summit event. In this edition, we cover:
- Agent copilot with auto-assist
- Demo Video
- Help center: Using auto assist to help agents solve tickets
- AI agents - zero training engine
- Demo Video
- Help center: Use Cases (Zero Training)
- AI-powered knowledge
- AI insights and reporting
- Voice AI:
- Analytics dashboard builder
- Demo Video
- Help center: Working with the dashboard builder (Beta)
Check out all the videos on the YouTube playlist to see these capabilities in action 📹 🤓. Also, if you want a deeper dive into key announcements from the AI Summit, be sure to join our upcoming Webinar: Zendesk AI Summit Deep Dive.
For even more product news, check out our monthly What's New summaries and our weekly release notes.
Posted Oct 17, 2024 · Jeremy Korman
0
Followers
3
Votes
0
Comments
Jeremy Korman created a post,
Hello Zendesk Users,
We are excited to present the Q2'2024 edition of our Product Spotlight series! We're here to highlight five brand-new features to elevate your CX. In this edition, we cover:
- GenAI: How to monitor your team's usage with the new pre-built dashboard
- Zendesk WFM: Big enhancements to roles, permissions, and audit logs
- Zendesk QA: How to monitor voice calls and AI agent interactions
- Custom Objects: How to use tools like data importer, dynamic filters, and object triggers
- Advanced Routing Queues: Steps to setup secondary overflow groups
Check out all 5 videos on the YouTube playlist to see these capabilities in action 📹 🤓
1) GenAI: How to monitor your team's usage with the new pre-built dashboard
More info: Overview of the Generative AI Agent Tools dashboard
2) Zendesk WFM: Big enhancements to roles, permissions, and audit logs
More info: Managing WFM roles & permissions, Announcing WFM Audit Logs.
3) Zendesk QA: How to monitor voice calls and AI agent interactions
More info: Voice QA and Announcing quality assurance (QA) for AI agents
4) Custom Objects: How to use tools like data importer, dynamic filters, and object triggers
More info: Announcing enhancements to the data importer, Announcing dynamic filtering for lookup relationship fields on tickets, Using custom objects in ticket triggers
5) Advanced Routing Queues: Steps to setup secondary overflow groups
More info: Announcing custom omnichannel routing queues
For even more product news, check out our monthly What's New summaries and our weekly release notes.
Edited Jul 23, 2024 · Jeremy Korman
0
Followers
2
Votes
0
Comments
Jeremy Korman created a post,

Hello Zendesk users!
We're excited to introduce you to our brand-new community topic: Product Spotlight! This is your ultimate place for the latest and greatest that Zendesk has to offer.
Here's how you can make the most out of this community topic:
- Quarterly Updates: We'll be sharing key product updates and enhancements right here, and you can expect these insights on a quarterly basis. Stay ahead of the curve by knowing exactly what's new and how it can benefit you.
- Demo videos: To make things more insightful and easier to understand, we'll accompany these updates with demo videos. Watch our experts walk you through new features and functionalities to help you get the most out of your Zendesk experience.
- Stay notified: Want to be the first to know? Simply click the "Follow" button on this page. By doing so, you'll receive an email notification every time we post new content. This way, you'll never miss out on important updates.
- Dive deeper: For those who love details, you can access a full list of every feature release by visiting our help center or checking out our release notes. It's a great way to get comprehensive insights into all the improvements and new additions.
We're committed to keeping you informed and empowered with every enhancement we make. Your feedback is invaluable to us, so as you explore the new features and updates, let us know your thoughts and experiences.
Thank you for being part of our community. Let's unlock the full potential of Zendesk together!
Stay updated. Stay ahead. Welcome to Product Spotlight ✨
Edited Jun 20, 2024 · Jeremy Korman
4
Followers
56
Votes
0
Comments
Jeremy Korman created a post,
Want to get up to speed on the biggest features Zendesk released in the last few months?! Check out these videos:
Check out the help center for the full list of product updates.
Edited Mar 01, 2024 · Jeremy Korman
4
Followers
4
Votes
0
Comments
Jeremy Korman created a post,
Want to get up to speed on the biggest features Zendesk released in the last few months?! Check out these videos:
Check out the help center for the full list of product updates.
Edited Feb 07, 2024 · Jeremy Korman
3
Followers
2
Votes
0
Comments
Jeremy Korman created a post,
Want to get up to speed on the biggest features Zendesk released in the last few months?! Check out these videos:
Check out the help center for the full list of product updates.
Posted Feb 07, 2024 · Jeremy Korman
5
Followers
3
Votes
0
Comments
Jeremy Korman created a post,
For a full history of our updates, check out the help center and release notes
Edited Feb 07, 2024 · Jeremy Korman
4
Followers
1
Vote
0
Comments
Jeremy Korman created an article,
This article includes the following topics:
- How is natural language processed?
- How are articles selected for recommendations?
- Common misconceptions
Related articles:
How is natural language processed?
AI agents use artificial intelligence to evaluate articles, which means that it is able to mimic human behavior. The AI agent uses natural language processing (NLP) to read every article in your help center and to understand the main concept behind each article. It then takes all the concepts from all the articles and places them on a map. Each concept gets its very own “address” on the map so that it lives near other, similar concepts. However, instead of just city, street, and zip code, this address has 500 parts. Whenever a new question comes in, the AI agent does its best to understand the concept that the question is asking about and use the map to determine the closest existing article.
For example, here are some concepts that might be extracted from a few questions:
Question | Possible concept |
---|---|
How do I dump my tickets to a file? | Exporting Data |
I’m locked out of my account | Account Access / Password Reset |
How do I create a crane? | Folding Origami Birds |
Note that the AI agent automatically detects the language used in an email by combining the subject and description and using language prediction. This may cause suggestions to appear in a language that doesn't match the one set in the end user's profile.
How are articles selected for recommendation?
When an incoming question closely matches with an existing article, they become “neighbors” on the map (as described above) and it’s clear that the AI agent should recommend the article. However, when the closest match is a few streets over, or in a nearby neighborhood, it becomes less certain that the concepts are related.
The data science team at Zendesk carefully monitors and has finely tuned this over time by adjusting a “threshold knob”. This threshold is not adjustable by admin or agents, it’s only accessible to the Zendesk development teams. The threshold knob is a global control, meaning it affects all accounts. It's used to determine how closely two concepts must be on the concept map to be considered similar concepts.
When the threshold knob is turned up, the AI agent becomes more conservative and will recommend fewer articles but the recommendations are more likely to be relevant to the question. However, this also means there will be more questions without any recommended articles or help center content. When the threshold knob is turned down, more content is presented, but it's less likely to be relevant to the end user.
Common misconceptions
There are some common misconceptions that can lead to confusion. In this section, we’ll address these misconceptions and hopefully clear some things up.
- Does the AI agent learn based on end-user feedback? Isn’t that where the machine learning comes in?
- Is AI-powered search always better than a keyword search?
- Can I “train” the AI agent by asking the same question and answer over and over again, and responding with “Yes” or “No” to mark an article as relevant or irrelevant?
- If I add labels to my articles, is that like adding a keyword to the article? Can this be done to boost how often an article is suggested?
- If I can’t use the “improve answers” button to improve performance, how can I improve performance?
Does the AI agent learn based on end-user feedback? Isn’t that where the machine learning comes in?
Although it's powered by a machine learning model, this does not mean that the AI agent is constantly learning. The model does not incorporate feedback in real-time from end users or agents. Therefore, the feedback has no influence on which articles are recommended.
The end user feedback is captured and used in a number of ways:
- It is displayed to agents to provide additional context on what articles were viewed, marked as “not helpful,” or used to resolve a case
- It is exposed in reporting for admins to track performance
- It is evaluated by the data science team at Zendesk
If you see that the incorrect articles are repeatedly being recommended, the best thing to do is modify the titles and the first 75 words of the articles to make the main concept more clear. You can also create a list of articles to draw from by using labels so that suggestions come from a sub-set of articles.
Is AI-powered search always better than a keyword search?
Overall, AI-powered article recommendations are more accurate and relevant than a keyword search, especially when the question is asked as a full sentence (instead of one to three words).
Can I “train” the AI agent by asking the same question and answer over and over again, and responding with “Yes” or “No” to mark an article as relevant or irrelevant?
No. The AI agent will consistently recommend the same articles regardless of any feedback from agents or end users. It is specifically built so it doesn’t require any training to get started. It’s already pre-trained to understand natural language. If you test out a phrase or question and the wrong articles are recommended, the best thing to do is modify the titles and the first 75 words of the articles to make the main concept more clear.
If I add labels to my articles, is that like adding a keyword to the article? Can this be done to boost how often an article is suggested?
Labels are a great way to create a list of approved articles to pull from. However, labels do not have an influence on the weight given to each article. See Best Practices: Using labels to optimize your article recommendations.
If I can’t use the “improve answers” button to improve performance, how can I improve performance?
The best way to improve AI agent performance is to consider the following:
- Monitor your autoreply with articles activity: Use Explore to see which articles are your best and worst-performing.
- Consider the structure of existing articles: Look at your help center articles and make sure that the content is concise and well organized. Each title should be phrased as a short sentence or a question.
- Use Content Cues: Use machine learning technology and article usage data to help you discover opportunities and tasks that will improve the health of your knowledge base.
Edited Feb 03, 2025 · Jeremy Korman
2
Followers
32
Votes
30
Comments
Jeremy Korman created an article,
In this Explore recipe, you'll learn how to create a dashboard that shows detailed information about what customers are asking Answer Bot and which articles are being recommended.
This article contains the following sections:
What you'll need
Skill level: Intermediate
Time required: 25 minutes
- Editor or Admin permissions (see Adding users to Explore)
- Zendesk Guide Professional or Enterprise with the Answer Bot add-on
Creating the report
In this section, you'll build a table showing detailed information about the last 100 Answer Bot tickets. In addition, you'll make the article names clickable so that viewers can go straight from your report to the relevant article.
To create the report
- In Explore, click the reports (
) icon.
- In the Reports library, click New report.
- On the Select a dataset page, click Answer Bot > Answer Bot - Article Recommendations, then click Start report. The report builder opens.
- In the Metrics panel, click Add.
- From the list of metrics, choose Answer Bot answers > Attempts, then click Apply.
- Next, create the attribute that will display the article title as a link to the article itself. In the Calculations menu (
), click Standard calculated attribute.
- On the Standard calculated attribute page, name the attribute Article and enter the following formula:
LINK([Article translation URL],[Article translation title])
The formula window will look like the following example:
Tip: If you're working in a language other than English, read this article to help you enter Explore formulas in your language. - When you are finished, click Save.
- In the Rows panel, click Add.
- From the list of attributes, choose the following:
- Ticket > Ticket ID
- Time - Ticket created > Ticket created - Date
- Ticket > Ticket status (the status of the Support ticket that was created)
- Answer Bot answer > Answer status (The status of the suggestion provided by Answer Bot, for example, Unoffered, Offered, Clicked, or Resolved)
- Calculated attributes > Article (the standard calculated attribute you created previously)
-
Answer Bot answer > Answer enquiry
To see all of the available metrics and attributes for Answer Bot, see the article: Metrics and attributes for Zendesk Answer Bot.
- When you are finished, click Apply. Explore displays the table. The next step is to perform some extra work to make the article titles link to the relevant article in your Help Center. From the chart configuration menu (
), choose Chart.
Tip: If you have a large Zendesk instance, you might have a very high number of Answer Bot attempts which Explore cannot load. If this is the case, consider using a date filter to restrict the amount of results that are returned. - On the Chart page, from the Text interpretation drop-down list, choose HTML.
- Ensure that the Clickable URL box is checked. Now, whenever you click an article name in the table, your web browser will open that article in a new tab.
- Now, add a top/bottom filter to show only the last 100 Answer Bot attempts. From the result manipulation menu (
), click Top/bottom.
- On the Top/bottom page, enable Top and configure the top value to be 100. Click Apply.
- From the result manipulation menu (
), click Sort.
- On the Sort page, click Z-A, then click Apply.
- Finally, give your report a name like Last 100 Answer Bot tickets, then click Save.
Your finished report will look similar to the following example:
Creating the dashboard
Now your report is complete, you'll add it to a dashboard along with three filters that enable the dashboard viewer to filter the results by answer status, answer channel, and ticket status. Once the dashboard is complete, you can share it with others in your organization.
To create the dashboard
- In Explore, click the dashboards library icon (
).
- In the Dashboards library, click Create dashboard.
- On the Start a dashboard page, select Blank dashboard, then click Select.
A new, blank dashboard opens. - From the Add menu, choose Report.
- From the list of reports, choose the report you created previously, Last 100 tickets. The report is added to the dashboard. You can drag and resize the report to make it look how you want.
- Now, you'll add three dashboard filters to let viewers filter the results by answer status, answer channel, and ticket status. From the Add menu, choose Data filter.
-
On the Choose data filter columns page, enable the Answer status attribute and configure the following values:
- Display: In a drop down
- Enable Multiselection
- Enable Select valuesThe Answer status attribute indicates the status of an answer provided by Answer Bot. Possible values include Unoffered, Offered, Clicked or Resolved.
- When you are finished, click Apply.
- Add a second data filter. This time, enable the Answer channel attribute and configure the same settings as you did for the first filter.
The Answer channel attribute is the channel on which Answer Bot interacted with the end user. Possible values include Email,Web Widget (Classic),Web form,API,SDK, and Slack. - Add a third and final data filter. This time, enable the Ticket status attribute and, once again, configure the same settings as you did for the first filter.
The Ticket status attribute is the current status of the ticket itself, for example, Closed, Open, etc. - Click the title of the dashboard and name it Answer Bot last 100 tickets.
- You'll now have a dashboard showing your report and the three filters you added. Drag and drop the items on your dashboard until they resemble the example below:
The dashboard is now complete. You can add more reports to it, add company branding, or share it with others. For more help with all things dashboard-related, see Creating dashboards.
Further reading
For more information to help you creating Answer Bot reports, see the following articles:
Edited Dec 17, 2024 · Jeremy Korman
2
Followers
13
Votes
13
Comments