JIVA Gadget

Inspiration

The new world will be where everything is compressed and overloaded compared to the present time. Businesses and markets, teams and managers, communication and transferring vast amounts of data - all of them will be in search of keys to the door of efficiency. The future of business communications looks to us as a multimodal, natural language based, and will also include a new type of player: such as intelligent virtual assistants. They will bring communication to the next level between teams and online services.

What it does

Add-on provides a natural language interface for Jira task management.

How we built it

We saw tremendous growth and potential of Artificial Intelligence and Machine Learning technologies worldwide. So we started with an R&D project earlier this year and invited a few students to be our Data Science engineers. After the war in Ukraine began, we held our activities for about one month but then resumed work. We decomposed a problem solution into several independent technologies to solve them step by step. As soon as Atlassian opened its yearly hackathon, we decided to provide this technology as a stand-alone product.

Challenges we ran into

We should learn a lot of new words and terms like dataset, models, training, and some specific application architecture. Mixing technologies is always challenging, but adding Artificial Intelligence is the hardest our cross-functional team has ever dealt with.

Accomplishments that we're proud of

Add-on brought a qualitatively new experience for Jira users. Managers can do the work just by talking to someone like another human. Teams can track the progress on the go and be informed about important project updates. Mobile devices can now be used effectively and bring a new level of interactivity and transparency.

What we learned

Integration and utilizing AI/ML technologies is much more complicated than we estimated on a project start.

What's next for JIVA Gadget

This technology has significant potential, so we have many items on our roadmap. The quality of natural language conversion should be improved, and the list of commands/intentions virtual intelligent assistant can recognize and handle will be enhanced.