Disclaimer:
|
When the chat widget pops up, you will be prompted to ask a question first, after posting the question, the “Get in touch” button will appear in 3-5 seconds.
Querying just the keywords can provide good results. You don’t need to enter a full sentence.
For example:
Keywords | Equivalent Question |
Period over period analysis | How do I create a period over period analysis? |
Total column, bar chart | How to add a total's column to a stacked bar chart? |
Dimension as measure | How do I show dimension as measure? |
Replace model | Replace the model of my dashboard |
Troubleshooting issues is similar to how you typically conduct research on search engines:
If you encountered an error with error message, you can post the error message to the chatbot
If it’s an issue without an error message on the UI, such as schedules are not sent, cache are not refreshed etc., you can post the symptoms
If it’s an issue and the troubleshooting might require understanding the use case or background, please reach out to us.
You are always welcome to get in touch with our support analyst for further questions.
There are 3 possibilities this could happen:
We don’t have an article for a close relevant use case or solution, when you connect to our support analyst, please feel free to request this resource.
Not hitting on the right keywords. Based on our test, the chatbot performs better when we query using keywords, expanding the enquiry by adding general phrases or terms can sometimes reduce the suggestion accuracy, such as “how do I”.
The question is not in English. Currently our chatbot and our articles only support English. In the future we might support other languages.
Please feel free to share your feedback or raise issues when you are with our support analysts.
If this happens during Monday to Friday, this might be due to the browser cache or browser extensions. Please try to login to Looker in the incognito mode and try again. If the “live chat” option shows up in the incognito mode, you can clear the browser cache or disable any browser extensions. If the issue still persists, please reach out to us.
If this happens on Saturday and Sunday or any public holidays, that indicates our live chat support is closed, you can come back again the next business day when the live chat is available or just leave us a message. Find more details about our support time
This might be due to the browser cache or browser extensions. Please try to login to Looker in the incognito mode and try again. If the chat widget works in the incognito mode, you can clear the browser cache or disable the browser extension. If the issue still persists, please leave us a message using the customer portal.
Today, authorised users can reach Looker support via the in-product chat widget. Our chat support has been available to both developers and admin users for Looker related technical requests. Working with the Looker support team has been considered helpful for developing Looker knowledge and resolving technical challenges. On the other hand, we have heard some feedback from our customers on the following topics:
Quick questions are not always quick: the solution to your question might have been documented in our knowledge base, however you might have to take time to go through the conversation with our analysts and wait before you get the answer.
Explaining all your pre-chat research when you talk to the agents: You have done lots of pre-work before chatting to our agent, however it might be time consuming to make sure the agent is aware of your request and knowledge level before they can jump into the investigation/solution.
To address the above problems, we are going to add a machine learning powered chatbot support layer on top of our current chat support.
When you initiate the chat widget, you will be able to ask questions to the chatbot, and the chatbot will suggest relevant articles from our Help Center. If the suggested article answers your question, you can directly apply the solution. In case the suggestions do not fully answer your question, you can still get in touch with our support analysts.
Save time for quick questions: you get answers instantly, no need to wait for the support analyst to get back to you.
Fully take advantage of our content resources: Our Help Center is the one-stop-shop where you can find the most common questions and use cases, you don’t need to go to different places again for an answer.
Our chat support is still available 24/5 via the chat widget; you can reach out by clicking on the “Get in touch” button.
Our documentation, Help Center, and Community Technical Tips section are still publicly accessible and will continue to support you.
Our chatbot can be helpful for “How do I” type of questions:
How do I do XYZ in Looker? (How do I create cohort analysis in Looker?)
What is XYZ about? (What is Aggregate Awareness and how does it work?)
What’s the best practice to achieve XYZ? (What’s the best way to migrate a project to a new git repo?)
I got an error, what does it mean and how do I troubleshoot it? (How do I fix “Unknown or Inaccessible Field”?)
Greetings: Our chatbot is specifically for helping identify relevant solutions based on the question context, currently it’s not able to respond to greetings and any other type of conversations. When you have any questions, you can get directly into the point.
A complete replacement of your own research: our chatbot is able to index all Looker documentation and knowledge base articles, however due to the diversity of Looker use cases, we cannot guarantee that all use cases are covered, though we will continually add more resources.
Very customized use cases/investigation that requires context understanding: for use case or investigation that requires an understanding of business or technical context, reaching out to our support analyst might be the best option.
Reporting a bug or sharing product feedback: we suggest talking to our chat agents for raising and troubleshooting bugs, while using the product ideas platform for feature requests.
High priority requests: for high priority requests such as performance and data issues, please reach out to our support team directly.
Most of the articles suggested by our chatbot have been reviewed by our team; they are trusted knowledge resources created by Looker consultants and analysts. Some of the articles might include outdated information which are subject to limited support.
When you view any suggested articles, the chatbot will collect your feedback by asking you to confirm if it’s “Helpful” or “Not Helpful” with two options at the bottom of the chat widget. Please share your feedback, that will help us improve the suggestions accuracy.
We actively track the requests and solutions to ensure we are surfacing the most useful content. However, if you have any particular resources/article you would like to see on our Help Center, please feel free to share the feedback with our support analysts via chat or webform
All your users who are permitted to use chat support will receive the chatbot service. We cannot selectively switch off the chatbot for a particular user.
I'm afraid something along those lines:
https://community.looker.com/looker-adoption-community-1016/can-someone-confirm-looker-laying-off-us-dcl-29178
I really hope the BOT does not lead to a deterioration of support.
Hi @moebe ,
Thanks for your reply and sharing the concern.
The chatbot will be an add-on layer to our current support for making finding documentation and public resources easier. Our team is still available for providing in-depth help.
As Looker integrates with Google Cloud, we are confident we have the resources in place to support our customers in the best way possible. If you have questions, please reach out to your account team for more information.
We would love to hear your feedback regarding the chatbot, please PM me anytime!
Best,
Xin
@xin - Thanks for the info.
I can’t see the chat bot nor do I have the chat option available. Can you speak to this post about the chat option not appearing?
https://community.looker.com/got-a-question-79/support-chat-option-is-gone-in-my-instance-of-looker-...