2026 ASEE Annual Conference & Exposition

Work in Progress: GUIDE—An AI-Powered Co-Pilot for Student Academic Pathways in Engineering

Navigating the undergraduate engineering curriculum presents a significant challenge. In the Electrical and Computer Engineering (ECE) program, students must manage a dense network of prerequisites, technical electives, and specialization areas. At our institution, the curriculum is highly flexible, which, while offering choice, further complicates the process of selecting appropriate courses. This complexity is compounded by non-intuitive university software and fragmented information sources, forcing students to consult multiple platforms. The result is a planning process that imposes high cognitive load, increases the risk of administrative errors, and can even delay graduation. Moreover, without structured guidance, students may complete their degrees without developing expertise in a coherent area.
Existing digital planning tools have attempted to address these issues but largely serve as passive repositories. Existing foundational tools have centralized course data and improved user experience. However, they still place the burden of synthesis, validation, and long-term planning on the student. A clear gap remains for systems that move beyond static access to deliver proactive, intelligent, and personalized guidance.
To bridge this gap, GUIDE (Guided University Interface for Degree Exploration), an AI-powered co-pilot for academic planning is developed. At its core, GUIDE employs a Neo4j graph database that models the entire ECE curriculum as an interconnected network of courses and requirements. This knowledge graph powers a Retrieval-Augmented Generation (RAG) engine, ensuring that all AI-generated recommendations are grounded in verified curricular data, thus mitigating the hallucinations common in standalone large language models. Unlike a conversational chatbot, GUIDE integrates directly into the planning interface to deliver real-time, context-aware feedback.
The platform emphasizes unobtrusive but actionable support. Once students create an academic profile, GUIDE automatically generates tailored recommendations, suggesting complementary courses aligned with declared interests (e.g., machine learning, analog devices). It can also generate a complete, degree-compliant plan. All plans are validated through the Profile Evaluator, a rule-based engine that checks selections against complex program requirements and provides immediate, actionable feedback.
GUIDE advances beyond passive tools toward an active guidance system. By automating the logistics of degree compliance, it reduces cognitive load, prevents costly errors, and empowers students to chart optimal academic pathways. Early testing with undergraduate students has been highly encouraging. In a pilot survey, all respondents reported satisfaction, describing GUIDE as a step toward addressing a long-standing gap in our program. Most students also highlighted its user-friendly design. Peak usage is anticipated during the first week of January, when peak planning activity occurs; the results from this larger deployment will be included in the full paper. This work explores the potential of AI-powered guidance to deliver a more intuitive, supportive, and personalized academic planning environment, ultimately transforming the engineering student experience by making planning more intuitive, reliable, and student-centered.