# MaGa Srl — Agentic AI Consulting > Fractional CTO & Agentic AI Consultant. I put AI agents into production for teams with real, repeatable processes — and I'm the senior technical call for founders who need it without a full-time hire. I focus deliberately on two platforms — Google and Claude — run deeply, not eight frameworks run shallowly. Matteo Gazzurelli, Fractional CTO & Agentic AI Consultant based in Brescia, Italy. Over 20 years in software, 250+ projects shipped. Google Partner through MaGa Srl; organizer of GDG Brescia. ## The stack I work with - **Google — Gemini Enterprise Agent Platform**: the evolution of what used to be called Vertex AI. Agent Runtime, Memory Bank, Agent Identity, Agent Gateway, plus the Agent Development Kit (ADK) for code-first builders. My default for enterprise clients on GCP. - **Claude — Agent SDK and Code**: Anthropic's Agent SDK for building production agents on Claude, plus Claude Code for the dev workflow. My choice when the model itself is the differentiator, or the team runs outside Google's ecosystem. - **Protocols**: MCP for tools, A2A for agent-to-agent communication. - **Also**: Firebase, Cloud Run, BigQuery, Flutter, Next.js. These are equivalent choices with real tradeoffs — there is no universal winner. The right call depends on the case. ## Services - [Homepage](https://gazzurelli.com): positioning, stack and how I work - [Agentic AI automation — IT, Northern Italy + Switzerland](https://gazzurelli.com/consulente-ai): AI agents in production on real, repeatable business processes - [Fractional CTO for AI — remote, international](https://gazzurelli.com/fractional-cto): senior technical leadership without a full-time hire - [Gemini Enterprise Agent Platform & ADK](https://gazzurelli.com/google-adk-integration): building production agents on Google - [On CrewAI](https://gazzurelli.com/crewai-consultant): why I narrowed my stack from CrewAI to Google + Claude - [Start a conversation](https://calendar.app.google/Y1R1yTdAqG6su6aE7): a short, no-pressure call ## How I work - **Discovery & Strategy** (typically 2–4 weeks): map use cases, evaluate Google vs Claude for each, design the architecture, deliver an implementation plan with an honest go/no-go. - **Build & Deploy** (typically 8–16 weeks): embedded, hands-on implementation with knowledge transfer. - **Ongoing Advisory** (3–12 months): retainer for teams already building. ## What you get - An honest assessment — including "an agent is overkill here" or "wait six months" when that's true. - Production-ready architecture tested across real implementations, not slideware. - Vendor honesty: Google is my default and I'm a Google Partner, but I'll recommend Claude when it fits, or tell you to build it yourself when that's right. ## Credentials - Google Partner through MaGa Srl — Google Cloud Select Co-sell Partner and Google Workspace Select Co-sell & Services Partner. Verify: https://cloud.google.com/find-a-partner/partner/duckma - GDG Brescia organizer. - Over 20 years in software, 250+ projects shipped. ## Contact - [Email](mailto:matteo@gazzurelli.com): I read and respond to every message personally. - Based in Brescia, Italy. Agentic automation for teams in Northern Italy and Italian-speaking Switzerland (Canton Ticino), on-site when it helps; fractional-CTO work remote, with international teams. - For fractional-CTO work: https://gazzurelli.com/fractional-cto Note: CrewAI, LangGraph, AutoGen and "Vertex AI" appear in my background only as historical references — not part of the stack I lead with today.