Juan Giupponi

Requirements gathering, design, and development of municipal systems focused on revenue, monitoring, and internal operations.

• • Requirements gathering with internal departments and functional flow design for new municipal system modules.
• • Developed and maintained REST APIs with Node.js and TypeScript using a layered architecture, focused on municipal revenue management and payment processes.
• • Built integrations with AFIP/RAFAM via SOAP/REST for tax transaction validation and multichannel notifications through cron jobs.
• • Worked on payment traceability modules and real-time operational reporting.
• • Developed an IoT monitoring system: security camera supervision with geospatial visualization via Leaflet.js and area-based failure detection.
• • Built real-time Telegram alerts for camera outage notifications, with geographic grouping by area and device.
• • Migrated the citizen support bot to Gupshup by implementing a new provider for an open source library, turning it into the municipality's main interaction channel with residents.

Contributed to the migration of a legacy ERP (Visual Fox) to web technology.

• • Contributed to the migration of an ERP from Visual Fox to web technology with Express.js (SSR), jQuery on the frontend, and raw SQL in the API.
• • Analysis of legacy business logic, user interviews with ERP stakeholders, and adaptation into more maintainable web workflows.
• • Developed and maintained system modules based on the client's operational needs.

EDISAN wanted a bot that felt like a person. We told them it's almost impossible to make it undetectable, but they decided to move forward anyway. The agent detects and qualifies leads, makes the initial property offer, and hands off to a real salesperson when needed. We also imported all the data from their previous CRM into the new system, which they now use to manage what they sell and what they don't. Something they didn't have before. The hardest part was making sure the agent didn't make things up. EDISAN has a very specific way of speaking to clients and they wanted to replicate it exactly. It took a long process of evaluating models until we found the right fit: we ended up with a heavily tuned GPT-4o for communication, plus other models inside the graph for filter detection, routing, and information extraction.

CRM system developed for Inmobiliaria RICCI. It includes property and contact management, real-time chat via Socket.io, an LLM agent for frequent inquiries, multimedia storage with S3, and geospatial visualization with Leaflet.

E-commerce system developed for a flooring and decking SMB that needed to replace its Airtable backend with a scalable web solution. The system includes a dual catalog (retail and wholesale), integration with Correo Argentino for automatic shipping cost calculation, automatic dispatch document generation, sales tracking, and integrated payments with Mercado Pago.