GLUU: Brevo & Email Automation Execution

Project Overview This project focuses on designing, configuring, and executing an automated email communication strategy in BREVO for Gluu, leveraging the existing Figma Design System as the foundation for visual execution. The initiative aims to create targeted email workflows that engage new users, followers, subscribers, and current clients through personalized communication aligned with their journey and growth within Gluu platform. The project integrates BREVO with Gluu’s existing infrastructure (SUPABASE) to deliver contextual, data-driven email experiences that drive user engagement, retention, and platform adoption.

GLUU - Referral Program Project

This document outlines the creation of a comprehensive Referral Program designed to drive user growth and engagement on the Gluu platform. The program will reward users with "Gluu Points" for actions that result in successful network expansion, such as generating clicks on referral links and prompting views of shared collections. These points will function as a versatile in-platform currency, redeemable for discounts on monthly subscription fees, rental service fees, and future trade fees .

Dify Chatbot Optimization for Gluu - Data-Driven Engagement & Workflow Excellence

Objective: To optimize the existing Dify chatbot on Gluu.Repair, enhancing its effectiveness in engaging users, streamlining workflows, providing valuable client insights, and leveraging a data-driven approach for continuous improvement. This includes building a fully coded Admin Panel and integrating Brevo email subscriber data.

GLUU - SELL Feature Project

Project Overview This document outlines the project to design, develop, and integrate a "Sell Feature" into the Gluu platform. This feature will empower users to list their tokenized assets for sale across multiple major online marketplaces simultaneously, directly from their Gluu account. The project will focus on creating a streamlined UI/UX for the selling process, from listing and management to the eventual archival of the sale. It will also lay the foundational concepts for transferring an asset's digital history to a new owner, with future integrations for trade and blockchain verification. Goals The primary goal is to provide users with a centralized and efficient tool to sell their physical assets, enhancing the value of the Gluu platform as a comprehensive asset management solution. We will visualize and build a user-centric interface that simplifies cross-platform selling. This project aims to deliver a robust backend that can communicate with various marketplace APIs and a system to securely archive sale information. Objectives The team should be able to design and implement a system that allows a user to: Connect their Gluu account to multiple third-party marketplace accounts (e.g., Facebook Marketplace, Poshmark, The RealReal). Create a single sale listing that can be pushed to several marketplaces at once. Manage active listings across all platforms from a unified dashboard. Archive a completed sale, recording key details like final price, date, and marketplace. Conceptualize the user flow for a new owner to accept the item's digital history post-sale.

Analytics Project | Gluu | Aug 19th, 2024

Project Overview Gluu is shifting its focus to develop a robust Admin Dashboard, a critical internal tool for managing the platform and its users. The key objective is to create a centralized interface that provides deep insights into user activity and content engagement. Goals This project will apply data analytic tools and methodologies, centered around PostHog, to build, assess, and optimize Gluu Admin Dashboard. The object is to deliver actionable insights based on user data, content metrics, and onboarding funnels to enhance administrative decision-making and improve overall platform performance. Objectives The team should be able to analyze user behavior, content trends, and system-wide statistic to: Identify user engagement patterns and pain points within the platform. Quantify the effectiveness of the user onboarding process. Recommend data-backend improvements for user management and content strategy. Create dashboards for monitoring key platform metrics.

Gluu | Rental & Collection Page

Project Overview This project introduces a new core functionality to the Gluu platform: private, shareable "Collections" designed for renting assets. Users will be able to group their items into distinct collections, manage their privacy, and invite specific individuals to view and request to rent the contents. The system will manage the entire rental lifecycle, from the initial request and date availability to owner approval, notifications, and the final archival of the rental history. This feature aims to unlock new value for users by allowing them to monetize their assets within a trusted and controlled environment. Goals The primary goal is to build an integrated system that allows users to organize their assets into private, rentable collections. We will develop a secure sharing mechanism and a seamless request-and-approval workflow for rentals. The project will provide owners with robust tools to manage bookings and availability, while offering renters a simple and clear way to browse and request items. A key objective for the admin side is to gain visibility into platform-wide rental activities to gather valuable business insights. Objectives The team will design and implement a system that enables a user (Owner) to: Create, name, and manage multiple "Collections" of their assets. Set privacy for each collection and invite specific users (Receivers) via email. Manage rental availability for each item on a calendar. Receive, review, and respond to rental requests within a 48-hour window. Apply pre-defined discounts to rental requests (e.g., for duration or quantity). Log completed rentals as part of an asset's permanent history. The system will enable a user (Receiver) to: View a collection they have been invited to. See item availability on a calendar and request to rent one or more items for specific dates. Receive notifications confirming their request has been sent and when it is approved or declined.

Watch Brand Classification Model Enhancement

This project aims to enhance the predictive accuracy of an existing watch classification model deployed in AWS SageMaker. The current model, while functional, requires optimization to improve its ability to accurately identify watch brands from images. By utilizing an open-source dataset of watch images, learners will apply advanced machine learning techniques to fine-tune the model. The goal is to develop a refined model prototype that demonstrates a significant and quantifiable improvement in brand identification accuracy. The project will be conducted entirely within the AWS SageMaker environment, providing learners with hands-on experience in a real-world cloud-based machine learning platform. This project offers an excellent opportunity for learners to apply their classroom knowledge of machine learning and cloud computing to a practical problem.

Integrating AI and Cloud Infrastructure for Enhanced Asset Management

Gluu is in the process of enhancing its technological infrastructure to streamline operations and improve asset management. The project involves updating an Amazon EC2 instance to support the integration of advanced AI models and cloud services. The primary goal is to integrate the Dify Bot into Supabase for efficient data management and Vercel for a responsive front-end interface. This integration will facilitate real-time learning and condition reporting for Gluu's real-world assets, leveraging a Multi-Modal AI model. The project aims to provide learners with hands-on experience in cloud computing, AI integration, and front-end development, applying their classroom knowledge to solve real-world problems. Key tasks include configuring the EC2 instance, setting up the Dify Bot, and ensuring seamless communication between Supabase and Vercel.

Optimizing Cloud Infrastructure for On-Demand LLM Deployment

Gluu.Repair is seeking to enhance the efficiency of its cloud infrastructure by optimizing the deployment of large language models (LLMs) on Amazon EC2 instances. Currently, the models are running continuously, leading to unnecessary costs. The goal of this project is to explore and implement solutions that allow these models to be triggered only on demand, thereby reducing operational expenses. Students will investigate the potential of using Amazon Bedrock or other cloud providers to host the LLMs more efficiently. Additionally, the project involves gaining a deeper understanding of embedding techniques in QDrant, a vector database, to improve data handling and retrieval processes. This project provides an opportunity for learners to apply their knowledge of cloud computing, machine learning, and database management in a practical setting.