TL;DR The upcoming JASP version (due to appear this week) will bring a fully integrated AI. Use an API key to hook up your own LLM and take advantage of its ability to propose and conduct new analyses, annotate the results inside JASP, and explain statistical concepts you may have forgotten.

On Friday June 26th, Henrik Godmann and I presented JASP at the “Praxistag Qualität” at the Fraunhofer Institute for Manufacturing Engineering and Automation (IPA) in Stuttgart. This was an inspiring, well-organized event that gave us the opportunity to demo our recent break-through development in JASP: a fully integrated AI. Below is Henrik presenting while interacting with the AI:  

Our flyer explains the JASP AI in detail. The flyer sections are discussed below.  First, here is the header:

What is particularly appealing about this AI is that it can control the JASP interface. This means it can create or adjust analyses, interpret and annotate output, and be ready for interaction from within a JASP AI chatbox.

The JASP AI is different in the sense that you can use your own AI model, the analyses are guardrailed by the JASP GUI, you can restrict the AI action tools, and you have full workflow support:

In JASP, we have three pre-defined persona’s: Alfred the Advisor, Socrates the Tutor, and Evelyn the Explainer. In the JASP Preferences menu, you can set up your own persona!

In my own experience, Alfred is exceptionally helpful. In the near future we will expand on our new AI functionality in multiple ways.

As mentioned earlier, free community access requires a user-provided API key/model. Teams and institutions can contact JASP Services B.V. for full support.
NB: AI can make mistakes. We recommend verifying AI advice for important decisions.

Authors

Eric-Jan Wagenmakers (CEO) and the JASP Services BV Team.