Freelancers using Apps ScriptFreelancers using Apps Script
AI Integration & Automation Engineer | Full-Stack Web Apps
$50k+
Earned
66x
Hired
4.9
Rating
132
Followers
AI Integration & Automation Engineer | Full-Stack Web Apps
AI Video Creator | Automations Engineer | AI SaaS Developer
$50k+
Earned
13x
Hired
5.0
Rating
383
Followers
AI Video Creator | Automations Engineer | AI SaaS Developer
Kodable founder, Full Stack Developer passioned for AI
5.0
Rating
43
Followers
Kodable founder, Full Stack Developer passioned for AI
Cover image for 🎯 The Challenge
Selection Friction &
🎯 The Challenge Selection Friction & Decision Paralysis: Traditional wine e-commerce filters are overwhelming for non-expert buyers who struggle with complex sommelier terminology. Custom Conversational AI Engine: Training and integrating an LLM capable of accurately understanding domain-specific wine terms, tasting notes, and meal pairings in real-time. Ground-Up Architecture: Building a high-performance web platform and API infrastructure capable of linking conversational chat outputs directly to live inventory, cart systems, and checkout flows without latency. 🛠️ What We Developed 1. 🏗️ Custom Web Platform (Ground-Up Build) Designed and engineered a modern, high-performance web application tailored specifically for wine and gastronomy sales. Built a clean, mobile-first responsive interface with custom product cards, filtering systems, and order management workflows. 2. 🍷 AI Sommelier Engine Implemented a custom LLM-based recommendation pipeline trained on detailed wine metadata (tasting notes, grape varieties, body, acidity, aging, region, and food pairings). Enabled natural-language inputs (e.g., "I'm having grilled salmon tonight and need a crisp white wine under $30"). 3. 💬 Digital Wine Chat Assistant Integrated a real-time interactive chat module with streaming responses (via WebSockets). Embedded interactive product cards directly inside the chat interface, allowing users to add AI-recommended bottles to their cart with one click. 4. ⚡ Seamless E-Commerce & Inventory Integration Connected the AI assistant directly to real-time database stock levels, pricing tiers, and checkout pipelines. 💻 Tech Stack & Architecture LayerTechnologies & ToolsAI & NLP IntegrationOpenAI API, Custom LLM Prompt Engineering, Vector Embeddings, LangChainFrontendReact.js / Next.js, Tailwind CSS, WebSocketsBackend APINode.js, Express.js, REST APIDatabase & CachePostgreSQL (Wine Catalog & Metadata), Redis (Session Caching)Deployment & CloudDocker, Nginx, Linux / AWS 📊 Key Results & Business Impact 100% Custom Delivery: Successfully launched a complete end-to-end platform built from scratch. 40%+ Engagement Rate: Over 40% of unique site visitors actively consult the AI Sommelier during their browsing session. +28% Higher Average Order Value (AOV): AI-generated food pairing and multi-bottle suggestions significantly increased order size. Reduced Cart Abandonment: Instant conversational guidance eliminated choice paralysis, driving higher checkout conversions.
1
75
Full-Stack Developer | React, TypeScript, Node.js, APIs
6
Followers
Full-Stack Developer | React, TypeScript, Node.js, APIs
Business Systems Architect | Roadmap & GSheets & Automation
5.0
Rating
2
Followers
Business Systems Architect | Roadmap & GSheets & Automation
Google Sheets & Data Automation Expert
Google Sheets & Data Automation Expert
Google Analytics, Meta Pixel | Server-Side Tracking Expert
Google Analytics, Meta Pixel | Server-Side Tracking Expert
Senior Web Front End Engineer
Senior Web Front End Engineer
Cover image for There is much arguing everywhere
There is much arguing everywhere about jobs. JOEF (Job Opportunity Email Filter) is a Google Apps Script that I am developing in order to filter the deluge of job alert emails originating from various job boards (like LinkedIn or Indeed). Most of the job positions that these services claim to be a fit with your expertise and your preferences are, in fact, false positives. Such services ignore, possibly on purpose, many of your preferences (one among others, the work location type: "remote", "hybrid" or "on-site") and fail to match the job position accurately with your experience profile. JOEF fills that gap. Coded in pure JavaScript, linted with ESLint, formatted with Prettier, bundled with esbuild, and with only one runtime dependency: linkedom, a lightweight DOM API for email body parsing. Since I deployed it in November, it filtered thousands of job postings, and discarded more than 3/4 of them that didn't match my expertise or my preferences. - It can be fine-tuned through a number of user preferences, included various blacklists and whitelists for companies, professional titles, languages, skills, locations, etc... - It has a basic plugin system that permits to add parsers for any possible job board mailing list. - It uses Google Maps service to normalize locations. It can detect the job posting language and discard it if it doesn't match your known languages. Soon I will add a partner script to periodically scrape the job posting pages and collect further information in order to perform a second filtering step with the full job description and data (often, more strict residency requirements or language skills are not visible in the email excerpt). And I plan to add support for analyzing the job posting using AI, even local models, running on Ollama. JOEF has been coded by me, often with the assistance of AI models. If anyone is interested in my coding abilities, feel free to contact me.
4
2
78