Software, architecture and AI, from someone who works with them every day.
Tools, architectural choices and news from the AI world, seen through the eyes of someone who uses them on real projects. In English and Italian.
Who writes
Field experience, written for people who build
Every article comes from a real project: a tool tried in production, an architectural choice that held up or did not, a piece of AI news looked at beyond the announcement.
The goal is to give developers, tech leads and decision makers what they need to understand what really changes in their work, without hype and without shortcuts.
- Author
- Ranieri Vannozzi
- Experience
- Enterprise development, cloud and technical leadership
- Publishing
- Articles in English and Italian
- Topics
- Development, architecture, AI and project management
Experience
Who the author has worked with
Over more than fifteen years the author of HeroHubs has worked with companies across different sectors, sometimes directly and sometimes as part of larger teams, contributing to the development of their technology solutions.
Articles
Latest articles
Reflections on tools, architecture and artificial intelligence, written from real projects.
AI
October 2026
Claude Design and Pomelli: the brand as context an AI can read
Claude Design derives a team design system from its code, Pomelli derives a small business Business DNA from its website. Two different products reach the same conclusion: consistency does not come from the prompt but from a profile extracted once and reused every time.
Development
September 2026
Performant npm: the package manager that rethinks node_modules
Performant npm is not just a faster npm. The global store with hard links and the strict node_modules structure change the way a JavaScript project declares and uses its dependencies.
AI
August 2026
Paperclip: building AI agent companies with an org chart
Paperclip lets you design an org chart of AI agents that collaborate like the departments of a real company. A CEO, a writer, an engineer, an editor and a designer who split the tasks, work in parallel and ask for confirmation when it matters.
AI
August 2026
DeepSeek locally: integrating an open model into SaaS without paying for APIs
Running DeepSeek on your own machine turns the variable cost of APIs into a fixed hardware cost. A reasoning on when it pays off, how it is done, and which other open models to evaluate for next-generation intelligent SaaS.
AI
August 2026
Claude Science: when the assistant walks into the lab
Anthropic launches Claude Science, an environment that links more than sixty scientific databases and coordinates specialised agents for genomics, proteomics, and computational chemistry. Not a more capable model, but a new way of working for researchers.
AI
July 2026
Sakana Fugu: when value lies in orchestration, not in the model
Sakana Fugu is not a new AI model but a small seven-billion-parameter orchestrator that coordinates existing models. The value shifts from computational power to the ability to orchestrate.
AI
July 2026
The .claude folder: the control centre of Claude Code
The .claude folder is often ignored, yet it is where the behaviour of Claude Code on a project is actually defined. Understanding its structure means moving from correcting the tool to configuring it.
Development
June 2026
Conventional Commits: the commit message as a technical document
Writing commit messages freely is a convention that forms through inertia. Conventional Commits replaces it with a structure that generates value automatically.
Development
June 2026
Brute force protection: authentication that holds
A brute force attack is not sophisticated, but it is persistent. Building a solid defence is an architectural question first, a configuration question second.
Method
The principles of the blog
Five rules that apply to every article, from the first to the last.
From the field
Only what has been used on real projects, not what the slides promise.
Beyond the announcement
Every piece of news is read for what it changes in everyday work, not for the noise it makes.
Concreteness
Precise names, numbers and examples instead of generic formulas and vague promises.
Two languages
Every article is published in English and Italian, with the same content and the same care.
AI as a tool
Drafting and translation are AI-assisted, review and responsibility stay with the author.