Assess Student Work Using BoodleBox Features

As AI becomes an integral part of students’ academic work, educators must adapt their assessment methods accordingly. This guide will walk you through practical strategies for using BoodleBox’s features to assess students’ engagement with AI tools. By leveraging these assessment techniques, you’ll be able to provide meaningful feedback, ensure academic integrity, and foster a learning environment that embraces AI’s potential.

Overview of BoodleBox Assessment Features

1. Shared Chats: Students can submit a chat using a Chat Link which enables a professor to see and understand the process by which the student engaged with AI within that chat.
2. Chats to Knowledge: Professors can add shared chats to “Knowledge” which enables the professors to assess chats using AI.
3. Shared Folders: Students can submit a Folder of chats using a Folder Link which enables a professor to see and understand all the chats within that folder, including how the student(s) engaged with AI and peers within the chats.
4. Folders to Knowledge: Professors can add shared Folders to “Knowledge” which enables the professors to assess Folders of chats using AI.
5. Folder Statistics: Educators can view detailed statistics on student engagement within a Folder of chats, including breakdown of number of chats, prompts, messages, and bots used.
6. Assignments to Knowledge: Professors can directly upload the final products from assignments to “Knowledge”, which enables the Professor to assess the assignments using AI.

Qualitative Analysis

By reviewing shared folders and chats, professors can gain deep insights into student learning processes, critical thinking skills, and AI literacy development. 

• Reviewing student-AI interactions within chats reveals how students approach problem-solving, formulate questions, and refine their ideas through collaboration with AI.
• Analyzing the quality and effectiveness of student prompts provides opportunities for targeted feedback on their ability to communicate with AI and elicit relevant information.
• Tracking student interactions with AI over time allows educators to assess the development of their understanding of AI capabilities, limitations, and ethical use.

Connecting professors with shared chats, also allows them to provide personalized feedback, offering specific, actionable insights to support students’ unique learning needs and foster growth in AI-integrated learning.

Quantitative Analysis

Understanding student engagement, participation, and performance is simplified when reviewing Folder Stats. These stats can be viewed by clicking on any shared folder.

• Tracking metrics such as the number of chats, prompts, and messages provides a clear picture of each student’s level of involvement and effort in AI-integrated learning activities.
• Analyzing quantitative data helps identify trends in individual student engagement and compare them to class averages, enabling early identification of students who may require additional support.
• Monitoring the diversity and frequency of bot usage offers insights into students’ understanding of different AI tools and their ability to choose appropriate resources for specific tasks.
• Quantitative data on message count and prompt frequency serves as an indicator of the depth and persistence of student engagement with course topics and AI-assisted learning.

Rubric Application

By applying a rubric to students’ AI chats and final work product, educators can conduct comprehensive, consistent, and multi-dimensional assessments of student work in AI-integrated learning environments.

• Applying rubrics to both the final work product and the AI interaction process provides a complete picture of student performance, considering not only the end result but also the learning journey.
• Professors can create tailored rubrics that align with course goals, assessing dimensions such as the quality of AI collaboration, critical thinking, prompt engineering, and final output.
• Leveraging AI to help apply rubrics across all student submissions ensures a consistent evaluation process, mitigating potential biases and promoting fairness in grading.
• Utilizing multiple bots for rubric application offers diverse viewpoints on student performance, providing a more comprehensive and nuanced assessment.

Through deep analysis of the students’ final work product along with the process, educators can gain a holistic understanding of student learning in AI-integrated environments. These insights support personalized feedback, targeted interventions, and the cultivation of essential AI literacy skills, ultimately enhancing the educational experience and preparing students for success in an AI-driven world.