Projects using OpenAI in CanadaProjects using OpenAI in CanadaAI Voice Assistant Workflow for Call Automation
I built a complete AI voice assistant workflow using VAPI to help businesses handle calls faster, follow up with leads automatically, and reduce manual calling work.
The system can be used for customer support, appointment booking, sales follow-ups, lead qualification, reminders, surveys, and technical support. Instead of relying on a person to answer every call or manually contact every lead, the AI assistant can respond, guide the conversation, collect information, and route calls when needed.
The workflow includes AI assistant setup, phone number connection, inbound and outbound call configuration, call scripts, objection handling, transfer rules, testing, and performance tracking. This makes the system practical for real business use, not just a demo.
The final setup gives businesses a scalable voice automation system that can improve response time, capture more leads, support customers more consistently, and track call performance through metrics like total calls, average call duration, and minute usage.
This project shows my ability to build AI automation workflows that connect voice AI, business processes, and operational tracking into one complete system. Full-Stack Engineer --> Grant Navigator
Built an AI-assisted platform that helps Italian SMEs discover, qualify, and track government grants across multiple public sources.
What I delivered: • Multi-source grant aggregation and structured search • AI-powered relevance scoring and natural-language summaries • User accounts, saved opportunities, and onboarding flow • Clean UI for browsing funding programs and eligibility filters
Impact: • Centralizes scattered public funding data into one interface • Makes complex grant language understandable and actionable • Designed for real startup and SMB workflows
Tech: Next.js, TypeScript, Supabase, Vercel, OpenAI API
What this project shows: Product execution, data aggregation, UX clarity, and practical AI integration to solve a real information-navigation problem. ESA Copilot – AI Assistant for Environmental Reports
Tech: GPT-4o, Python, Node.js, React, RAG, Pinecone, Meilisearch, CV-based parsing
At Langan Engineering, I led the development of ESA Copilot, an internal AI system that accelerates Phase I Environmental Site Assessments (ESAs). The tool analyzes decades of environmental documents, including scanned PDFs, maps, regulatory records, and auto-generates report sections with audit-ready accuracy.
I built a custom RAG pipeline integrating LLMs, vector search, full-text search, and image-based document parsing. I also built the internal UI for prompt testing, report preview, and in-line editing. 
