Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{195329,
        author = {Chappidi Pranush Reddy and Byatha Sai Vardhn and Bollu Sai Praveen and Bellana Yashwant kumar},
        title = {FinalprepAi: AI-Powered Cognitive Interview Twin for Scalable Interview Preparation},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {283-290},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=195329},
        abstract = {FinalprepAi deals with scalable technical interview preparation using a Cognitive Interview Twin (CIT) model, based on real time video-based mock interviews and automated scoring. Its methodology uses browser-native Web Speech API to perform speech-to-text transcription (88.7% accuracy), structured Q&A generation and engineered Mistral Large Language Model assessment with Cohen Kappa of 0.91 among expert assessors (precision 92, recall 89). The binocular Siamese-inspired architecture integrates the multimodal performance information, including technical correctness, speech clarity, confidence measures, and delivery pattern, through the secure authentication with one-click signup and the cloud database storage. Statistically significant improvement of performance (54-71 percent correct) was observed as a result of longitudinal tracking with 54 percent to 71 percent correctness in three sessions (p<0.01), with end-to-end latency of less than 20 seconds and 100 percent uptime during pilot deployment. The main innovations involve adaptive question sequencing, where historical error patterns are used to create multidimensional feedback and communicate strengths and gaps in technical domains, and progress tokenization, which is applied to skill domains. FinalprepAi is deployed with interactive UI to connect with users, secured backend and top Large Language Model’s (LLM) with low latency have been used with we can removes evaluator bias and provides quantifiable skill growth to technology job applicants.},
        keywords = {Preparation of mock interviews, speech-to- text, LLM assessment, Cognitive Interview Twin, performance analytics, Video mock interview, GenAI for Mock interview},
        month = {April},
        }