Flo Hofmann

Quality Engineering Business Analysis AI Automation

I help teams deliver reliable software and automate repetitive work with AI.

With 18 years of experience across software quality, business analysis and technology delivery, I connect business needs with practical technical solutions — from understanding the problem to making sure the solution works.

Explore My Work Download CV (PDF)

Sydney, Australia Contract roles Remote across Australia

Flo Hofmann
Flo HofmannSydney, Australia

Organisations I have done work for

  • TAL
  • AMP
  • BT
  • Volkswagen
  • Audi
  • TAP Air Portugal
  • Applause
  • NSW Small Business Commissioner
  • Teufel
  • Goodgame Studios

How I Create Value

Quality Engineering & Test Automation

I look beyond a passing test. I question assumptions, spot missing scenarios and check whether the result actually makes sense.

I use automation with judgement. I make testing more efficient and repeatable without blindly trusting the tools.

Business Analysis & AI Automation

I turn unclear problems into practical solutions. I challenge assumptions, clarify requirements and find better ways of working.

I put AI to work where it makes sense. I use tools like Power Automate and Copilot Studio to reduce manual effort, with checks and human oversight built in.

I don't stop when my part of the job is done.

When something doesn't add up, I investigate, involve the right people and follow it through to a working result. When I see repetitive work or an inefficient process, I look for ways to improve it. I often build my own tools, with or without AI, and share what I've learned so the whole team can benefit.

UnderstandImproveDeliverVerify

Selected Work

Three systems I built and tested, with the problem each one solved.

Diagram of the automation: an Excel input sheet, validation, terminal automation, a state check, a run ledger and a safe stop before the next client

Insurance Workflow automation

Linux Reflections Workflow Automation

Problem
A repetitive PAS anniversary workflow required hours of manual terminal navigation and data entry, with interruption creating duplicate, missed-work and recovery risk.
My solution
Built an Excel VBA automation using Reflection for screen observation and Windows key injection for actions, with controlled inputs, logging and rerun logic.
Evidence
Validated compile, navigation, single-client, round-trip and batch behaviour in the live system; rerun testing correctly skipped 83 clients already recorded as successful.
  • AI-Assisted Engineering
  • Quality Gates
  • Guardrails
  • Human-in-the-Loop
Diagram of the pipeline: Microsoft Teams capture, transcript retrieval and clean-up, then AI processing into a summary, decisions and actions by person, with ambiguity flags and human review

OIC Architects AI automation

Meeting Intelligence Pipeline

Problem
Teams transcripts captured important decisions and actions, but left them buried in recordings and unusable by the workflows that followed.
My solution
Built the transcript capture and processing pipeline, with structured notes, routing rules, ambiguity flags, human review and downstream action handling.
Evidence
Tested repeat processing and compared independent AI outputs, exposing duplicate transcripts and under-specified formatting rules. Fixes went into controls and specifications rather than blind model tuning.
  • Power Automate
  • Human-in-the-Loop
  • Guardrails
  • Failure Modes
  • Context Engineering
Diagram of how query quality is checked: interpret the business intent, construct the joins and conditions, then validate the generated SQL against the intended result

Insurance Test data

Natural Language SQL Query Engine

Problem
Complex test-data queries often required five or six tables; unfamiliar joins could fail or create hard-to-explain duplicate results.
My solution
Built a Copilot-based natural-language SQL engine, onboarding table relationships, field meanings and business rules around policies, lives and benefits.
Evidence
Used it on real test-data searches, checking generated queries against the intended conditions and distinguishing genuinely missing data from query-construction problems.
  • GitHub Copilot
  • Context Engineering
  • NL-to-SQL
  • Software Quality
View All Work
Flo Hofmann

About Flo

I have spent 18 years making sure software does what the business needs, as a tester, test manager and business analyst. I don't take a requirement as given. I ask whether it can be true and what is missing.

AI is the part of my work I enjoy most right now. I build with it in my own time, run it at OIC Architects, the Sydney practice I co-founded, and write up what I learn in my Thoughts and on LinkedIn.

Tools I use

  • Claude Code
  • GitHub Copilot
  • Copilot Studio
  • Power Automate
  • Playwright
  • Python
  • SQL
  • Postman
More About Me

Thoughts & Learnings

Notes from my own projects, mostly on testing AI agents and automating real work.

All Thoughts

Talk to me about a role

I'm open to contract roles in quality engineering, test automation, business analysis and AI automation, in Sydney or remote across Australia. Send me the role, and I'll give you an honest answer on whether I'm a good fit.

Get in Touch LinkedIn Download CV (PDF)
location
Sydney, Australia
work
Contract roles, remote across Australia
linkedin
/in/misterhofmann