Fractz

AI · Blockchain · European compliance

AI and blockchain systems for European business.

Engineered in Florence. Compliant by construction.

We design, build and ship the systems that automate operations and secure transactions — with GDPR and MiCA controls written into the architecture, not bolted on afterwards.

ERPCRMPMS · WMSSOURCE SYSTEMSIngestionAgent + modelEU-RESIDENTPolicy gateOperationsAudit log
Reference architecture — regulated AI deployment

Selected clients

  • 01Pellemoda
  • 02Arredo Quattro Industrie
  • 03Fattoria Dianella 1°
  • 04Empoli FC
  • 05H-Farm
  • 06Freename
  • 07Holding Morelli
  • 08GB Viaggi
  • 09Ita Build Srl
  • 10Enewatt

Built on

  • OpenAI
  • Claude
  • AWS
  • Google Cloud
  • Azure
  • thirdweb
  • Alchemy
  • n8n

What we do

Services for measurable results

We focus on ROI: rapid implementations, enterprise security, and cloud scalability.

Sectors

Vertical solutions

We speak your business language: proven use cases and clear KPIs.

Onboarding takes days because KYC, AML screening and CRM data live in three systems that do not talk to each other.

What we build

  • KYC/AML screening wired into your CRM, with sanctions and PEP checks on every application
  • An audit trail that reconstructs why an application was accepted or refused, not just the outcome
  • Tokenized instruments — bonds, policies — with transfer restrictions enforced on-chain

Regulatory exposure

AI used for credit scoring or insurance pricing falls under Annex III of the AI Act, now deferred to 2 December 2027. DORA already applies. We design the conformity evidence in from the start.

Typical first project
A KYC/AML integration on one product line — typically 6–8 weeks to production.
Average KPI
-40% onboarding time
Deployment
Implemented in 6 Italian regional banks in under 4 months.
Talk to an expert

Engagements

What we have shipped

All engagements

Each engagement, on the record: the system we built, how long it took, and what changed for the client.

  1. 01

    Fashion manufacturing

    Product operations for a leather goods maker

    Pellemoda S.r.l.

    A production platform the marketing team runs without engineering support

    System
    Digital product platform + operations automation
    Duration
    Multi-phase
    Read the engagement
  2. 02

    Education

    Marketing automation for an international college

    H-Farm College

    Manual marketing tasks automated; team time moved back to campaigns

    System
    Marketing automation + reporting
    Duration
    Multi-phase
    Read the engagement
  3. 03

    Travel

    Booking system and support bots for a travel agency

    GB Viaggi

    Booking and traveller support handled by the system rather than by hand

    System
    Booking platform + automated support
    Duration
    Multi-phase
    Read the engagement

Process

How we work

Three phases. Each one ends with something you can look at.

  1. 01

    Discovery & Audit

    Goal analysis, process mapping, and KPIs.

  2. 02

    Tailored build

    Rapid development with biweekly sprints.

  3. 03

    Deploy & Scale

    Monitoring, training, and continuous optimization.

The practice

Engineering discipline, delivered end to end

We operate as the engineering function our clients don't have in-house: architecture, build, compliance and handover under one delivery standard, across the EU.

01
Senior-led delivery
The people who scope your engagement are the people who build it. Weekly demonstrable progress against agreed measures — no status theatre, no handover to juniors.
02
European by default
EU-resident infrastructure, data processing agreements, and documentation your DPO and your auditor can both work from.
03
Fixed scope, fixed price
Discovery produces a written scope with a price and a date. Change requests are quoted, never assumed.
04
You own everything
Source, infrastructure and models are handed over on completion. No lock-in, no dependency on us to keep it running.

Testimonials

Insights

Notes from the work

All insights

Practical writing on AI, tokenization and EU regulation — for the people who have to sign off on them.

  1. 01

    26 Jul 2026

    Build vs Buy an AI Agent: An Honest Decision Framework

    When an off-the-shelf AI tool beats a custom agent, when it doesn't, and the four questions that decide it — from someone who profits from 'build' but will tell you to buy.

    abhishekchauhan.it
  2. 02

    09 Jun 2026

    LangGraph vs CrewAI: Which AI Agent Framework for Production? (2026)

    An honest, docs-grounded comparison of LangGraph and CrewAI — mental models, state and durability, human-in-the-loop, protocols, and which one to actually ship to production.

    abhishekchauhan.it
  3. 03

    18 May 2026

    Designing Agent Architecture with Memory: A Framework from Anthropic's Patterns and LangGraph's Primitives

    Anthropic defines how to structure agent workflows. LangGraph provides the memory primitives. Nobody connects the two. This post does — a practical design framework for matching each Anthropic agent pattern to the right LangGraph memory architecture.

    abhishekchauhan.it

Start here

Tell us what you want to build

Send the problem, not a brief. You get a straight answer on whether it is worth building — and what it would cost.

Get our AI Trend Report first

Join 500+ decision makers receiving weekly insights on real cases, KPIs, and operational roadmaps.