AI-POWERED ACADEMIC DEFENSE COACHINGSYSTEM
Abstract
Consider a study preparation program that is much more interactive than piling up the slides andreciting lines verbatim. This AI-powered web-based application was designed and developedforfinal-year student and supporting institutions web app. The platform integrates natural languageprocessing, speech, and gesture tracking which enables it to simulate defense sessions that feel
real. Students input a project summary vocally, and a machine learning-based examiner (AIexaminer) responds with personalized questions, evaluates responses and provides feedbackoncontent delivery, pace, tone of voice and confidence level. Every session is recorded andsaved, allowing users to review AI feedback, follow markers of performance over time, andseeprogress in an interactive transcript or modal page. Here is a bonus, any user who undergoesadefense practice session, can save such session which will be made available to everyonewhologs in. Users can select from a range of projects or defense sessions that wasn’t createdbythemfor a quick start demo and receive personalized feedback reports. Strict encryptionandauthentication of users keep personal information intact. With this AI-powered web app, studentsaren’t merely answering questions; they’re building confidence, refining delivery, andapproaching their defenses with the assurance of having faced—and learned from—a virtual
panel of experts.
Full-Text Access Notice
In accordance with the NERD Policy on promoting peer-reviewed publication, public access to the full text of a project, thesis or dissertation is restricted for three years, allowing the author and supervisors sufficient time to pursue peer-reviewed publication.
During this period, researchers with legitimate academic or research purposes may request authorisation directly from the author to enable NERD to release the indexed full texts of the work using the form below.