How to use the Well-Grounded AI Argument Analyzer
And the bigger point -- these systems can model reasoning for students and others, and I think that's pretty valuable?
So this is the thing I've been building. I think it's really cool. I'm a little out of practice presenting on video, but I just want to get people to try it. Let me know if the video is compelling or not to you -- I am going out to get grant funding on a related project, and would love to know.
(https://youtu.be/qSk8aZEcNlU)
Oh, and if you've been a fan of this work, please share. Like I said, I have a related grant that I am going to submit soon, and I could use the boost. I really do believe that this sort of thing (modeling reasoning) is a better use of AI in education than tutor chatbots and the like. And I’d like to get funding that would allow me to try and prove that point.
Here’s a direct link to the tool, if that’s your preference, though as the video shows you can find it by searching the Explore GPTs link on the ChatGPT sidebar.
https://chatgpt.com/g/g-679149b4f3348191935d05daa242e669-well-grounded
Thanks, Mike. I think this will be a very valuable tool for school librarians working with students. I will be sharing at my next training session on Tuesday.
I have taught the Toulmin analysis methods to students for nearly 30 years, so this resource is very exciting!
Two questions?
(1) How did you train the GPT to identify implicit warrants?
(2) Have you given any thought into the possibility of a "Toulmin coach" GPT that could aid students in working through their own argument analysis?