Create
cancel
Showing results for 
Search instead for 
Did you mean: 
Sign up Log in

Leveraging AI in Report Building

Evita Legzdina_eazyBI
Marketplace Partner
Marketplace Partners provide apps and integrations available on the Atlassian Marketplace that extend the power of Atlassian products.
May 15, 2024

With the rapid development of AI technology, we, at eazyBI, were keen to understand how to leverage this new trend to make report creation simpler. Looking at current AI technologies, they predominantly rely on large language models (LLMs), which have been extensively trained on vast amounts of internet text, enabling them to quickly generate similar content.

Would the same work in report creation? Not really.

Why?

Shifting from general AI applications to business intelligence (BI), the stakes are higher. When there is a question about the data or a report, you should not settle for an average answer. You want your report to be reliable since the business decision relies on the data.

Report builder assistant

When you are just starting with report creation you might be overwhelmed with the many measures and dimensions you can select from. To give you some ideas you can start by opening our report builder assistant on the Analyze tab and choose some sample prompt or write your own. As we have a vast library of sample reports and charts available, our AI assistant will find the report that most closely matches your prompt and display it on your data.

Let’s see the example of a query about created and resolved issues by month.

Screen Shot 2024-04-23 at 08.41.03.png

The assistant correctly translated the query to eazyBI measures “Issues created” and “Issues resolved”, and applied the correct Time dimension level and page filter. You can continue the chat with the assistant and ask to modify the created report or chart. You can ask to explain the measures to understand better what each of them will return.

MDX formula assistant

We’ve heard so many times that you love report creation with eazyBI, but MDX is something that many find intimidating. Now we have introduced the MDX formula assistant to make complex things easier.

Here again, our assistant will refer to our comprehensive documentation site with a guide on writing MDX formulas and descriptions of all available MDX functions.

The MDX formula assistant is located in the sidebar of the calculated member definition dialog. You can ask the assistant to write any formula you'd like, and it will provide you with the suggested MDX code. Links to the corresponding documentation pages with more details will also be provided.

Screen Shot 2024-04-23 at 08.59.18.png

If the generated formula meets your needs, feel free to use it in your calculation. If it doesn't, you can request a new response for alternative solutions, or you can continue the chat and provide more details on how to improve the calculation. Also, remember that the assistant can help you understand the formula to ensure it aligns with your needs.

Calculated custom field assistant

Did you know that instead of creating MDX calculations during report building, you can create additional custom field measures or dimensions during data import? It might sound on the complex side of eazyBI, and indeed it is. However, now you have a helping hand – an AI assistant, that can help you create a JavaScript code to extract the necessary data from the Jira issue.

Explain to the assistant which data you would like to extract from the issue, copy the generated JavaScript code, and test it with some issues.

Screen Shot 2024-04-23 at 21.58.55.png

 

You can learn more about how we’ve built our AI assistants on our blog, but there are a couple of things to keep in mind:

  1. Customer data imported into eazyBI are never sent to LLMs and are not exposed to any external services. Only user prompts and metadata about measures and dimensions are used in instructions, but the generated report definition is executed the same way as any other report created by users.

  2. Assistants, like any other current AI technology, can make mistakes and you should validate generated reports and formulas.

  3. eazyBI AI assistants (and we as we build them) are still learning. We’ve started with the initial set of questions that users might ask. Please help us by rating the answers they provide and leave a comment with your feedback.

  4. Remember that assistants can’t read your mind. Tell them exactly what you want. If you provide limited details, they will try to guess what you might have had on your mind.

  5. And finally—assistants are available 24x7 and are ready to help you any time. But our support is still more intelligent and eager to help you when you have more challenging reporting requirements. Please do not hesitate to ask for additional help from our support when the assistant can’t give you the right advice.

0 comments

Comment

Log in or Sign up to comment
TAGS
AUG Leaders

Atlassian Community Events