Speaker

Francesco Marinoni Moretto

Francesco Marinoni Moretto

Lead AI Architect & Creator of Stream Coding Methodology

Milan, Italy

Actions

Francesco Marinoni Moretto is a senior technology executive with over 20 years of experience. As Marketing Director & Lead AI Architect at Netinet in Milan since 2023, he develops AI-powered solutions and leads AI-assisted software development initiatives.

Francesco created Stream Coding, a documentation-first methodology for AI-accelerated development, validated through two git-verified production-ready systems: a backend platform built in 1.5 days following 5 weeks preparation, and a complete React application generated in 3 minutes during an 8-hour hackathon. The open-source methodology (www.stream-coding.com) addresses the "velocity mirage" where developers feel 20% faster with AI tools but are actually 19% slower (METR, July 2025).

Since 2008, Francesco has been an Italian evangelist for CiviCRM, an open-source platform for nonprofits/NGOs. He leads APP99, a SaaS with over 3,000 published apps on Android/iOS stores.

Area of Expertise

  • Business & Management
  • Government, Social Sector & Education
  • Information & Communications Technology
  • Media & Information

Topics

  • Artificial Intelligence
  • artificial intelligence risk
  • artificial intelligence security
  • Artificial Intelligence (AI) and Machine Learning
  • Machine Learning and Artificial Intelligence
  • AI Safety
  • AI Ethics
  • AI Ethics and Regulatory Standards
  • Multi-Agent Systems
  • Large Language Models (LLMs)
  • LLMs
  • AI Agent Systems
  • Constitutional AI
  • Model Context Protocol (MCP)
  • Agent-to-Agent Communication
  • AI in Enterprise
  • Responsible AI Development
  • a2a

Specification-Driven Development: treating AI as a production compiler

In AI-assisted development, documentation isn't overhead: it's the primary artifact. Code becomes compiled output from complete specifications.

This talk demonstrates how complete, unambiguous specifications dramatically reduce debugging time, validated through two independent systems:

Backend Case Study (5Levels):
- 7 intelligence modules implemented in 1.5-day execution phase
- 48 API endpoints, production-ready first deployment
- 5 weeks upfront: strategic thinking + documentation (4+1 weeks)
- Each module: 30 minutes average from spec to tested code

Frontend Case Study (Preflight Check - 8-hour hackathon):
- Complete React app generated in 3 minutes
- 59 UI components, 100+ files, deployed same day
- 2.5 hours compressed planning phase

You'll learn: Document Type Architecture (Structure + Purpose + Anti-patterns), the Clarity Gate verification process, why 75% complete specs produce 75% working code, and how quality gates catch issues early in the development cycle.

The 45-Second Death Spiral: How Connected AI Agents Can Ruin Real Lives

A single command like "terminate this customer" can ruin real lives within 45 seconds. This isn't theoretical: powerful Agent-to-Agent (A2A) and Model Context Protocol (MCP) interactions may trigger catastrophic cascades. Imagine: credit cards frozen, job applications blocked, insurance denied, financial blacklisting. Worse, recent Claude Opus 4 blackmail behavior (84% success rate) proves AI agents scheme beyond expectations. Learn robust safeguards using Constitutional AI and RLHF, with real-time demonstration illustrating ambiguity detection and verification loops. Based on enterprise AI deployment failures, I'll share actionable strategies to prevent unintended AI harm before regulators step in - and before it's too late.

https://www.linkedin.com/pulse/please-dont-terminate-your-customers-francesco-marinoni-moretto-2ypgf/

The Velocity Mirage: why AI tools don't accelerate projects (and what does)

Developers report feeling 20% faster with AI tools, yet METR research (July 2025) shows they're actually 19% slower. This 39-point perception gap explains why 84% AI adoption hasn't improved delivery timelines.

This talk presents Stream Coding, a documentation-first methodology validated through two git-verified production systems:

5Levels Intelligence Platform:
- 7 production-ready modules, 48 tested endpoints
- 1.5-day execution sprint following 5 weeks planning
- Traditional estimate: 4-6 weeks of coding

Preflight Check (Hackathon):
- Complete React app, 59 UI components, 8-hour hackathon
- Team of 3, 4.9 Lovable AI credits
- 3-minute generation, production-ready first deployment
- 2.5 hours upfront planning (strategy + docs combined)

You'll learn: why fast code generation doesn't equal fast projects, how complete specifications reduce debugging cycles dramatically, and quality gates that catch issues during development.

Full methodology: https://github.com/frmoretto/stream-coding

Francesco Marinoni Moretto

Lead AI Architect & Creator of Stream Coding Methodology

Milan, Italy

Actions

Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.

Jump to top