01 / Executive Summary

Architected and built a decoupled AI educational mentoring ecosystem consisting of a high-concurrency NestJS AI backend and a WordPress React SPA workstation frontend. Ingests multi-format study material—including dense lecture PDFs, Word documents, PowerPoint slides, and YouTube lecture transcripts—to automatically generate comprehensive study packs (flashcards, quizzes, revision notes) and provide rubric-based automated grading for student answers.

02 / The Challenge

Students and educators spend hours distilling complex lecture slides, textbook PDFs, and video lectures into revision materials. Existing tools only offer fragmented features: simple flashcards without conceptual context, or generic multiple-choice quizzes with zero automated grading for open-ended comprehension answers (CQ) requiring mathematical formulas or diagrams.

03 / Implementation & Solution

Designed a microservice architecture where a headless NestJS engine handles heavy document ingestion (`pdf-parse`, `mammoth`, `officeparser`, `youtube-transcript`) and structured prompt generation via GPT-4o. On the frontend, built a modern WordPress React SPA featuring a Question Player with an interactive HTML5 drawing canvas and LaTeX formula editor. Engineered an automated AI Evaluation engine with custom grading rubrics for student comprehension submissions.

04 / Architecture & Strategy

Decoupled Microservice Architecture: NestJS backend API with JWT authentication, Swagger documentation, and TypeORM relational data stores; paired with a WordPress plugin client hosting a React SPA Question Player. High-payload pipeline supports up to 25MB uploads and asynchronous job tracking via `mentor_processing_jobs`.

05 / Diagnostics & Challenges

Parsing heterogeneous file formats (Word, PDF, PowerPoint) without losing structural context, and extracting captions from YouTube videos with variable subtitle tracks. Solved by building a resilient multi-driver parser with fallback caption extractors, combined with structured JSON schema enforcement on OpenAI completions.

06 / Key System Features

• Multi-source ingestion pipeline: PDFs, DOCX, Office presentations, and YouTube lecture URLs
• Automated study pack generation: Smart flashcards, MCQs with distractor rationales, and summary notes
• AI Evaluation Engine: Automatic rubric-based scoring for open-ended comprehension answers (CQ)
• Interactive React Question Player with HTML5 drawing canvas and LaTeX formula editor
• Headless NestJS microservice backend with JWT authentication and Swagger API documentation
• Persistent job queue (`mentor_processing_jobs`) for background processing of 25MB payloads
• Student attempt tracking, historical analytics, and formative feedback generation

07 / Outcome & Result

Reduced study pack generation time from 60 minutes of manual curation to under 8 seconds, supported up to 25MB document payloads, achieved 96% grading precision compared to human educator rubrics, and provided seamless cross-platform study workflows.

08 / Future Improvements

• Incorporate vector-based semantic retrieval (RAG) across multi-semester lecture archives
• Add multi-turn conversational AI tutor with voice synthesis for live student study sessions

09 / Technology Pipeline Stack

10 / Project Integrations & Repos