The assessment of writing competency in French as a Foreign Language presents significant challenges due to the multidimensional nature of writing and heterogeneous evaluation practices. This research introduces an innovative framework integrating artificial intelligence and interactive visualization to support the formative assessment of writing competency. The developed Interactive Curves Graph system combines automated analysis with stakeholder engagement in a learner-centered approach. Through a qualitative study involving 15 French as a Foreign Language teachers across 3 primary schools in Morocco, we investigated the effectiveness of an AI-enhanced progress monitoring system. The participating teachers (mean age = 37.25 years, mean teaching experience = 17 years) implemented the system with 190 students across 7 classes. The methodology employed a design-based research approach, incorporating iterative development phases and comprehensive validation through teacher feedback and usage analysis. Data collection spanned 1.5 months and included semi-structured interviews, system interaction statistics, and detailed feedback analysis using ATLAS.ti coding, with two distinct examination periods. Results reveal three major contributions: (1) successful stakeholder integration through interactive visualization capabilities that support assessment objectivity, (2) AI-enhanced analysis facilitating pattern detection and immediate feedback, and (3) a multi-directional communication framework strengthening educational collaboration and decision-making. Teacher responses demonstrate that the Interactive Curves Graph system effectively addresses formative assessment challenges by combining computational rigor with pedagogical accessibility. This research advances theoretical understanding and practical implementation of digital technologies in writing assessment. The findings suggest that the developed approach can significantly enhance writing competency eAssessment practices while opening perspectives for broader educational applications. The study's limitations, including sample size and context specificity, indicate directions for future research in cross-cultural validation and longitudinal impact assessment.