Writing
Blog
Notes on AI, enterprise technology, digital strategy, and the projects I build.
Six Months of side projects with AI Coding Assistants: what worked, what didn't
The first answer from an AI coding assistant is a draft, not a solution. Here is how I learned to drive AI toward well-built code, and why it rarely gets there on the first try. Over the past six months I have built three side projects with AI coding assistants at my side: LLM-Sim, YaAICV, and Pocke
Why Public Sector AI projects fail
After 15 years selling and building technology for enterprises and public administrations, I've learned that AI projects almost never fail in the demo. They fail afterwards, for reasons that have little to do with the model. I have sat through hundreds of technology demos. Servers, storage, cloud, c
Law 132/2025 for Builders: Designing AI that supports the Decision-Maker
Italy's AI law says that in the Public Administration, AI must support the officer, never replace them. That sounds like a legal principle. It's actually an architecture. Here is how I would translate it into code. Imagine a municipal office using an AI agent to process building permit requests. The
Article 50 is live: What "You're talking to an AI" means for Public Services
Since 2 August 2026, the EU AI Act's transparency rules apply. The high-risk rules have been postponed. Here is what applies today, what comes later, and a practical checklist for a municipality's AI assistant. "Hi! I'm Giulia, your virtual assistant at the City of Foggia. How can I help you today?"
From Infrastructure Builder to AI Enabler: Why I joined Salesforce to transform Public Administration
In June 2026 I left Dell Technologies to join Salesforce as a Senior Account Executive for Public Administration. This is the story of that change, and why I believe AI is about to change how governments serve citizens. For most of my career I have built foundations. As an engineer, I designed netwo
LLM-Sim: Peeking inside a language model, one token at a time
There are plenty of articles explaining what a Large Language Model does. Far fewer show you exactly how it does it — step by step, probability by probability. LLM-Sim is a fully observable simulation of the LLM pipeline, built to make every internal decision visible and explorable in the browser. L
AI in Enterprise Sales: My Take After 15 Years in the Field
Having worked at Dell Technologies, Oracle, Check Point, and Vodafone, I've seen many technology waves. AI in enterprise sales is different — it's not just an efficiency tool, it's reshaping the entire buying process. By the time a prospect talks to a salesperson, they've already: Queried multiple A
PocketKid: A practical approach to teaching financial literacy through a Python-Powered PWA
In an era where digital experiences shape how children learn, traditional approaches to financial education often fall short. Concepts like saving, earning, and budgeting are typically introduced too abstractly, without a tangible system that connects effort to reward. PocketKid addresses this gap w
Building YaAICV: Designing an LLM-Powered CV optimization engine
From idea to architecture: a technical deep dive into building an AI-assisted CV optimization platform using LLM APIs. Modern hiring pipelines are increasingly mediated by Applicant Tracking Systems (ATS), transforming CVs from human-readable narratives into machine-parsed datasets. This shift intro