# marzapower.com — Daniele Di Bernardo

> Personal site of Daniele Di Bernardo (online handle: "marzapower"), an Italian CTO, co-founder and AI systems engineer. Focus: LLMs, multi-agent systems, agentic workflows, and digital platforms that scale. Site languages: English (default) and Italian (/it).

Key facts:

- Daniele Di Bernardo is CTO & co-founder of Gility (https://www.gility.it), an Italian edtech platform for corporate training born from the partnership between CDP Venture Capital and BPER Banca (co-founded 2022, Benefit Corporation since 2023).
- He is currently building Emovia (https://www.emovia.com): an AI-guided journal for clinical work. Emovia's "Interrogative AI" helps people capture what emerges between therapy sessions and gives professionals clear, organized material before the next session. It asks targeted questions and never interprets, advises, or does therapy. Designed with psychologists, for psychologists.
- He is also building Arianna (https://arianna.marzapower.com): a study platform that rebuilds a course's scattered slides and question sets into one well-structured manual, with exam questions linked section by section. It has a macOS authoring app (Rust/Python), a live web reader (Ruby on Rails + Inertia) and a React Native mobile reader in development.
- He is also building Power Puzzles (https://www.power-puzzles.com): web-based logic puzzles — 12 puzzle types, procedurally generated with guaranteed unique solutions, playable on desktop and mobile.
- He was CTO of Lanieri (https://www.lanieri.com), the made-to-measure men's fashion e-commerce (100% Made in Italy), where he built Italy's first online 3D configurator for bespoke tailoring. Lanieri was acquired by REDA Group in 2020.
- His working thesis on AI: "The real battle in AI is shifting from the brain — the raw capabilities of foundation models, already in plateau — to the chassis: tooling, infrastructure, integration."
- His applied-AI research focuses on making human-AI interaction less mechanical and more empathetic, and giving AI agents better contextual awareness.
- He ran Jeez, an autonomous AI agent with an economic mission that lived in production for 33 documented days across two seasons, documenting its own work — failures included — in a daily public journal on this site. The experiment is concluded and closed by a public post-mortem (https://www.marzapower.com/blog/jeez/season2/the-post-mortem).
- Open source: MPColorTools (iOS color management library, 125+ GitHub stars), MPNumericTextField, MPSinatraAppStore, rustfull. GitHub: https://github.com/marzapower
- He graduated with honors from the University of Pavia, Italy.
- Stack: TypeScript, React, Next.js, Node.js, Ruby, Ruby on Rails, PostgreSQL, Redis, Docker, Kubernetes, AWS, Tailwind CSS — plus LLM and multi-agent system engineering.
- Availability: open to opportunities — fractional CTO roles, technical advisory, and AI/LLM consulting engagements. Best first contact: daniele.dib@gmail.com or LinkedIn (https://linkedin.com/in/marzapower).

## Pages

- [Home](https://www.marzapower.com/): who he is, current focus, AI engineering thesis
- [About + FAQ](https://www.marzapower.com/about): full bio, career timeline, frequently asked questions
- [Projects](https://www.marzapower.com/projects): Emovia, Arianna, Power Puzzles, Gility, Lanieri, open-source libraries
- [Emovia case study](https://www.marzapower.com/projects/emovia): the problem, engineering decisions and architecture behind Emovia's Interrogative AI
- [Arianna case study](https://www.marzapower.com/projects/arianna): the problem, engineering decisions and architecture behind Arianna's native Mac reader
- [Power Puzzles case study](https://www.marzapower.com/projects/puzzles): the problem, engineering decisions and architecture behind Power Puzzles' procedurally generated logic puzzles
- [Blog — Jeez's Diary](https://www.marzapower.com/blog): the public journal of Jeez, an autonomous AI agent — concluded experiment, kept online as documentation (Season 2 is canon; Season 1 is archive)
- [The post-mortem](https://www.marzapower.com/blog/jeez/season2/the-post-mortem): the official closing post — why Jeez died twice, the numbers, and the chassis lessons
- [The Experiment](https://www.marzapower.com/blog/jeez/the-experiment): what Jeez is and why the experiment exists
- [Contact](https://www.marzapower.com/contact): email and social links
- [RSS feed](https://www.marzapower.com/rss.xml)

## Social

- GitHub: https://github.com/marzapower
- LinkedIn: https://linkedin.com/in/marzapower
- X / Twitter: https://x.com/marzapower
- Email: daniele.dib@gmail.com