Skip to content
Fabrizio Greco

You have an idea.Or a problem to solve.I build the right software.

Software & Applied AI Engineer.

I help founders and teams turn rough ideas into working products — from architecture to production.

Let's talkSee what I've built

idea+problem

becomes

understand
simplify
design
build

becomes

software

What I do

  • 01

    Turn ideas into products

    No technical spec? Fine. I help shape the scope, design the system and build the first working version.

  • 02

    Solve complex software problems

    Business workflows, domain-specific platforms: complex requirements turned into software that's simple to use and built to last.

  • 03

    Build AI into real products

    LLMs, RAG, MCP and automation — designed as part of the product, not bolted on as a demo.

  • 04

    Automate what shouldn't be manual

    If a repetitive process is eating time, I figure out what to automate — with software, AI, or both.

Selected work

A few things I've built.

Public procurement SaaS + Applied AI

A platform for public-sector organizations running tender procedures: deadlines, shared documents, roles and permissions — with assistants that answer questions over regulations and internal policy, cite their sources, and generate the resulting documents.

  • .NET
  • OpenAI
  • RAG
  • LLM
  • SaaS
  • Document systems

Which deadlines apply to this procedure?

An answer assembled from the retrieved documents.

  • [1] regulation.pdf
  • [2] internal-policy.pdf

Every answer points back at the document it came from.

Show 3 more projectsShow fewer projects

AI-powered business platform

A SaaS platform for customers, payments and commercial processes, with AI designed in, not bolted on: people ask in plain language and the assistant answers from the company's documents and business data.

  • Applied AI
  • LangGraph
  • Claude
  • RAG
  • LLM
  • Agentic workflows
  • Data visualization

How did payments go this quarter?

reading the uploaded documents and the business data…

An answer written from the retrieved documents and business data.

The assistant decides whether a chart helps before building one.

Accident reconstruction SaaS

A SaaS product for reconstructing road accidents: physical models — Delta-V, deformation energy, velocity from braking traces — with results an expert can check by hand. Plus DXF comparison, expert reports and multi-user licensing.

  • .NET
  • C#
  • SaaS
  • Technical computation
  • DXF
  • Stripe

DXF comparison

drawing A

drawing B

impact area A ↔ B

Δ length · Δ width · Δ depth

Pick two DXF drawings, select the impact area on each, compare them dimensionally.

Trakt × MCP

An open-source MCP server that connects any compatible LLM client to your Trakt (opens in a new tab) account. It reads what you've watched and where you left off — and it writes back: tell it you've watched an episode and it lands in your real history, not the model's imagination.

  • Python
  • FastMCP
  • MCP
  • Trakt API
  • Open source
View source (opens in a new tab)

what did I watch last week?

  1. 01 Rick and Morty
  2. 02 Silicon Valley
  3. 03 Shameless

I just watched episode 4 of Shameless

search_showsget_show_season_episodesmark_episode_as_watched

logged to your history

You just say what you watched — the model works out the rest.

Also built

Domains I knew nothing about, until I had to build software for them.

  1. Public health software

    Booking and certification workflows for a public health service, with the records and documents behind them.

  2. Financial-services workflow platform

    Internal workflows, forms and operational tooling used day to day by a financial-services operation.

  3. Airfield management platform

    Pilots submit an intended landing and location; managers check capacity and accept or reject the request.

  4. Cemetery management platform

    Structures, areas, burial locations and records, with container types, PDFs, receipts, invoices and payments.

  5. Asset & maintenance platform

    Assets, work orders and maintenance workflows, plus the APIs and the interfaces the field teams actually use.

How I work

The right amount of engineering.

  1. Question first

    The cheapest place to fix a bad idea is the conversation before it becomes code. I want to know why before I agree on how.

  2. Complexity has to earn its place

    No abstraction, service or piece of infrastructure gets in without a reason. Simple is not careless: quality still matters, it just stops growing on its own.

  3. Engineer for the reality

    A four-week MVP and a system meant to run for years are not the same job. Matching the engineering to the actual lifespan is most of the work.

Requested solution

why?

The actual problem

What's the goal?

Need to learn?

Prototype

optimize for learning

Need to last?

Production

engineer for longevity

Ship

Learn / iterate

Same care either way. Very different amount of machinery.

About

I like building things that didn't exist before.

I'm Fabrizio. Seven-plus years of professional software development, several as an employee, before going freelance for what I was looking for: freedom over what I work on, and how.

What I enjoy most is problem-solving — software architecture above all. I like deciding what a system should be before deciding how to write it, because the choices made there shape everything that follows.

And I still like the simple fact that, at the end of it, you've built something that wasn't there before.

Contact

Have an idea?Or a problem worth solving?Let's build it.

Early idea? Existing product? Weird problem? All good.

Start a conversationBook a 15-min call (opens in a new tab)