Projects
Explore selected projects showcasing practical work across data, automation, AI, and agentic engineering.
Corporate Project
2026
Automated quality-control system that uses AI to evaluate customer calls and WhatsApp chat transcripts against SOP, KYC, response-time, product-explanation, and fraud-detection rules, then logs structured results into Google Sheets with email and Excel reporting.
Personal Project
2026Source code
A reproducible PyTorch implementation of the LeNet-5 architecture, adapted for FashionMNIST while preserving paper-specific features such as sparse convolutional connections, trainable subsampling, scaled tanh activations, Euclidean RBF outputs, and discriminative MAP loss.
Personal Project
2026Source code
A repository-scoped automation runtime that enables command-line AI agents to create, edit, extract, render, and quality-check professional PowerPoint presentations through repeatable, cross-platform workflows.
Personal Project
2026Source code
A human-in-the-loop AI agent that plans, generates, reviews, illustrates, schedules, and publishes persona-aligned social content through Telegram and the official Threads Graph API.
Corporate Project
2025
Built an internal WhatsApp-based lead monitoring and AI analytics system for a fintech business, combining scheduled CRM alerts, anomaly detection, natural-language-to-SQL querying, chart generation, and automated reporting.
Corporate Project
2025
Built a WhatsApp Business chatbot and operator dashboard for a fintech service provider, combining Gemini-powered intake conversations, structured lead qualification, multimodal document handling, realtime human handoff, CRM synchronization, and operational analytics.
How public case studies handle scope, confidentiality, and project types.