Open to work Melbourne, VIC Permanent Resident · full work rights Hybrid / On-site / Remote AI & Automation Consultant
Proof of Work — show, don't tell

Giovanni Lesna-Maranetto

AI & Automation Consultant · Certified Management Consultant · 12+ years strategy + build

Most people who call themselves AI consultants can show you a slide deck. I can show you systems I've shipped — AI agents, self-hosted automation infrastructure, and human-in-the-loop workflows running real business processes. I work AI-augmented: I architect, review and ship fast because I pair deep solution judgement and op-sec with modern AI tooling. Outcomes are the proof. Below are short walkthroughs — each covers the problem, what got automated, where the human stays in control, and the stack.

what I've built — problem → solution → result · short demos
01 · automation infrastructure

Client onboarding that took a day now takes minutes

The problem

Setting up a new client's automation environment meant hours of manual server, security and software setup — slow, and every manual step is a chance to get something wrong.

What I built

A tool that builds the entire environment automatically from a single setup file — one command instead of a checklist.

The result

A full day of setup collapses to minutes — identical every time, with security built in from the start.

Kept safe: secrets locked in a vault, encryption automatic, hardening built in — not bolted on after.
under the hood: Hetzner · Cloudflare · Docker · n8n · infrastructure-as-code
Watch (2–4 min)
02 · AI with a safety rail

AI handles the incoming flood — a human still approves

The problem

Teams want AI to handle incoming requests, leads and tickets, but can't risk it sending the wrong thing to a customer on its own.

What I built

A workflow where AI reads each request, sorts it, and drafts the reply — then stops and waits for a person to approve, edit or reject before anything goes out.

The result

The repetitive reading and drafting is automated; a human keeps the final say — saving hours of triage a week without losing control.

Kept safe: the AI proposes, a person decides. Full record of what was suggested and what was approved.
under the hood: n8n · LLM · human-in-the-loop approval gate
Watch (2–4 min)
03 · data you can trust

A dashboard that proves its own numbers are right

The problem

People make decisions off dashboards every day — but a dashboard is only as trustworthy as the maths behind it, and most can't show that the maths is correct.

What I built

A live tracking dashboard with the key numbers up top, and an automated test suite that checks every calculation behind them.

The result

Decisions made on numbers that are verified, traceable and trustworthy — not just numbers that happen to look right.

Kept safe: every figure traces to a source, calculations are independently tested, data is versioned.
under the hood: single-page app · JSON data layer · 150+ automated tests
Watch (2–4 min)
04 · AI that respects your data

AI agents that run on your own machine — data never leaves

The problem

For many organisations the blocker to using AI isn't capability — it's that they can't send sensitive data to an outside AI service.

What I built

Custom AI agents that complete real multi-step tasks, running on an AI model hosted locally — plus deliberately limited access, so an agent can only do what it's allowed to.

The result

The same AI capability, but the data never leaves the building — AI you can put in front of a compliance team.

Kept safe: local model = data stays in-house. Agent permissions are scoped and constrained.
under the hood: AI agents (OpenClaw, Hermes) · locally-hosted LLM · scoped tool access
Watch (2–4 min)
capabilities --core
AI agentsworkflow automation business process automationn8n ZapierMakeRPA LLM integrationhuman-in-the-loop AI governanceAPI integration AWSDockerPython PowerShellSQL process optimisationdigital transformation stakeholder managementROI / business case
track-record --archive · enterprise delivery (the foundation under the builds)

Before the AI builds, the discipline. The same process mapping, requirements (BRS), UAT/production rigour, regulatory delivery and senior-stakeholder engagement is exactly why my automation ships and survives in production — not just in a demo.

banking · enterprise delivery

Untangling a bank's systems — and its regulatory reporting

The problem

A major bank had overlapping trading systems and complex tax-reporting obligations spread across many business units — costly, risky and hard to manage.

What I did

Merged three trading systems into one, moved core financial data onto a single modern platform, and automated regulatory (FATCA/AEOI) reporting across five business units — working with senior IT, finance and business leaders.

The result

Lower cost, less duplication, and regulatory reporting that runs reliably — delivered through proper requirements, testing and production rollout.

10+ business units · BRS · UAT · production · SAP HANA · Murex · SAFe 4.0
public sector · strategy & research

Helping government bodies prepare for the future of work

The problem

During COVID, multiple government departments needed to understand how ready they were for new technology and the changing world of work.

What I did

Ran a Fourth Industrial Revolution (4IR) readiness assessment across several government bodies, plus feasibility studies, large-scale surveys and executive research reports.

The result

Clear, evidence-based readiness findings and recommendations that senior public-sector decision-makers could act on.

via MB Consulting · 4IR readiness · feasibility studies · executive engagement

Let's talk

Resume, references (including Australian referees), and a live walkthrough available on request.