This dissertation investigates how collective process-oriented documentation tools, combined with Natural Language Processing (NLP) techniques, can enhance knowledge construction in hands-on, open-ended learning environments, such as makerspaces. Through a three-year design-based research, the study developed and tested a collective documentation interface and an NLP-powered learner-facing analytics dashboard to track and visualize students' knowledge construction throughout their making processes. Key contributions of this work include the design of tools that support both individual and collective knowledge construction by enabling students to reflect on their learning and observe others' processes, fostering collaborative learning communities. Natural language processing (NLP) techniques were applied to student documentation, extracting core concepts and visualizing their development over time, thus providing insights into the knowledge-building trajectories within the class. Additionally, the research examined student perceptions of AI-generated learning suggestions and their reactions to the dashboard, emphasizing the need for thoughtful and careful integration of AI in educational practices. The findings offer practical implications for the design of educational tools and environments that facilitate both immersive engagement and reflective oversight, in alignment with Edith Ackermann's idea of "dwelling in" and "stepping back" (Ackermann, 2001). These insights are critical for educators, researchers, and designers working to enhance the learning potential of maker education and project-based learning, especially considering the integration of Artificial Intelligence tools. [The dissertation citations contained here are published with the permission of ProQuest LLC. Further reproduction is prohibited without permission. Copies of dissertations may be obtained by Telephone (800) 1-800-521-0600. Web page: http://bibliotheek.ehb.be:2222/en-US/products/dissertations/individuals.shtml.]