Immerse in the business
Observe real work with the people doing it: goals, volume, friction, exceptions, workarounds and everyday decisions.
Reverse SDLC
Stop coding assumptions.
A practical playbook for IT development in the AI era.
Reverse SDLC surfaces business intent before agents accelerate implementation.
The method
Intent becomes the interface.
I immerse myself in your business, the problems you need to solve and the optimisation you are looking for. Twenty years across sales, hospitality, logistics, airport operations, credit-card back-office operations, pricing and business intelligence help me connect the human, operational, commercial and technical dimensions quickly.
The highest-return opportunities are often overlooked because they live closest to execution: in tasks repeated every day by frontline teams. A few minutes saved, one error prevented or one better-supported decision then compound at scale.
Return to first principles
Turn scattered documentation, tacit rules and the desired outcome into a coherent view of the system and its constraints.
Open the specs to experts
Set up a secure web application where domain experts answer questions, fill gaps and validate trade-offs.
Prototype to learn
Put the future system in users' hands so the specs improve and the right architecture is validated before investing in the MVP.
Build the MVP with agents
Direct AI agents inside explicit guardrails while I remain accountable for the model, architecture, code, security and tests.
Observe, correct, deploy
Test with users, instrument disclosed logs and AI interactions, correct quickly, then handle authentication, servers and production deployment.
I cover the entire chain: business discovery, specifications, prototypes, architecture, code, tests, authentication, servers and deployment. One accountable operator, reinforced by specialised AI agents.
Confidential programme · €80M-turnover business
A confidential ERP programme, one simple question: what must be true before we build?
For a confidential €80M-turnover business, the work begins by exposing exceptions, tacit rules and decisions that determine the architecture. The public outcome is not a screenshot: it is a method for reducing risk before production.
The agent is not the architecture.
Agents accelerate implementation when constraints, decisions and verification already exist. Human judgement remains accountable for business trade-offs, security and quality.