Live Now Streaming live — ask me to build anything, free, right now. Open on Twitch ↗
Want to chat? Drop a request: Join the chat →
overview

AI as a tool, not a data leak

Most popular AI tools learn from what you type — your documents and data can be stored and used to train models you don't control. I work differently: AI runs inside your environment, or on enterprise platforms with no-training, no-retention guarantees.

The pattern I build around is simple — AI absorbs the high-volume routine, and you stay in control of the judgment.

automate.py
# your data — your environment
agent = private(retain=false)
# absorb the routine
agent.handle("intake, drafts, routing")
# humans keep the judgment
escalate(edge_cases) you
✓ faster, private, in your control
what this can include

Ways I put AI to work

automation

Workflow automation

AI agents that handle document processing, data extraction, drafting and routing — with a human kept in the loop for the calls that need judgment.

private by default

Private & secure AI

Run inside your own environment, or on enterprise platforms with no-training, no-retention guarantees. No leaking your data to a public chatbot.

web

AI-built websites

I design and build sites from the ground up with AI in the loop — not dropped into a generic template. Custom, fast, and entirely yours.

content

Content, SEO & GEO

AI-driven content workflows tuned for search and for GEO — getting you found in AI-generated answers, not just traditional search results.

apps

Mobile & Google Play

Familiar with the full app lifecycle, including Google Play Store listings, signing and release — so your app actually ships, not just builds.

integration

AI in your product

Chat, search, summarisation and recommendations wired straight into the systems you already run.

proven across industries

What AI is already doing out there

A few publicly reported examples of the same pattern — AI handling the routine at scale while people keep the judgment.

customer service

Klarna

An AI assistant handled two-thirds of customer chats within a month, cutting resolution time from ~11 minutes to under 2 — with humans brought back for complex cases.

banking

Commonwealth Bank

An AI fraud agent helped cut fraud losses by over 20% year-on-year, screening 20M+ payments a day in real time while analysts focus on genuine threats.

public sector

Pennsylvania

In a state pilot, 175 employees across 14 agencies saved ~95 minutes a day with secure enterprise AI, with people kept at the centre of decisions.

back office

Document automation

A document-heavy firm cut processing time 75% and returned 30+ hours a week with an AI extraction pipeline — human review preserved where it mattered.

manufacturing

Visual inspection

AI vision holds 95–99% accuracy around the clock where manual inspection misses 20–30%; BMW has reported a 37% defect reduction.

agriculture

Selective harvesting

Vision robots pick only ripe fruit, gently, 24/7 — cutting post-harvest loss by up to 25% and filling a labour gap rather than displacing workers.

Figures as publicly reported. These are industry examples of what AI automation can do — not my own client results.

the stack

Tools & tech

A sample of what I reach for — not an exhaustive list, and I'll always use what fits your project best.

OpenAI / Claude APIs Python LangChain RAG / vector search Self-hosted models n8n / workflow agents Next.js Postgres

Got something to automate or build?

Tell me what's slowing you down, and I'll tell you straight whether AI is the right fit. First reply is free, no obligation.

message.sh
// or reach me at WhatsApp · +61 401 824 126
LIVE Ask Me to Build Something
Watch on YouTube Chat