Data science is emerging as a crucial 21st-century competence, touching many areas of professional practice, from arguing with evidence for social change to building artificial intelligence models. According to leading AI literacy frameworks, data literacy is a fundamental component of AI literacy. However, current efforts to build data science curricula and tools often rely on generic public datasets, which do not offer authentic and personally relevant learning experiences to students and teachers from non-technical backgrounds. This paper introduces a novel, interdisciplinary data science curriculum to scaffold middle and high-school students in undertaking real-world data science practices. Through project-based learning modules, our curriculum engages students and educators in possible solutions to community-based data challenges involving live sensor data collection, analysis, and visualization with the MIT App Inventor data science toolkit. We use a participatory data collection approach, allowing students to lead investigations on topics of personal interest, thereby fostering higher authorship proximity to the data. We draw on computational action and situated learning practices to expose students to hands-on methods that empower them to use data creatively and responsibly in evidence-based arguments. Through unplugged activities, they also explore personal connections to public data sets, gaining insight into the cultural layers that influence data collection and representation. The modules include adaptable assessment rubrics to help teachers (especially those from non-math and computing backgrounds) measure their students’ abilities to identify statistical patterns, critically evaluate data biases, and make predictions. These also assess the development of interpersonal and interpersonal competencies through the course of student data science projects. By teaching the practical application of skills, we hope to instill a sense of agency in students to positively impact their communities and the world using data science and AI.