AI & developer infrastructure

ERM migration powered by AI

Key achievements

Process optimisationModernization for growthEfficient onboarding

"I've been very impressed at their openness to innovate, their openness to collaborate. And not just be an organisation that's there to do what they're told, but an organisation that's there to make our organisation much more technologically stronger."

Matt Hyne, CTO at Protecht

Client

Protecht is a major Australian company helping organizations understand, monitor, and manage risk. For over 25 years, they’ve delivered enterprise risk management, compliance, training, and advisory services to governments, regulators, and businesses worldwide. Hotovo led Protecht’s ERM migration to a modern React stack, using AI code assistants to speed up the work.

Efficiency gains and cost-smart modernization

Case study

The need

Protecht, a leading enterprise risk management provider, wanted to modernize its core system to ensure long-term scalability, improved development speed, and better maintainability. Moving to a modern tech stack (React) was essential — but doing it efficiently, securely, and without interrupting ongoing development work was the real goal.

Core issue

Migrate a legacy system to a modern frontend stack without slowing down feature development
Keep the process cost-efficient and compliant with strict data security standards
Equip the development team with modern AI tools while avoiding steep learning curves or productivity drops
Select the right tools from a rapidly evolving AI ecosystem

Our solution

Hotovo led the end-to-end ERM migration using AI code assistants to boost development speed and reduce manual work. Our team:

Analyzed and selected trusted, secure AI tooling for code assistance. The aim was to migrate a vast number of UI screens to eliminate the old technology stack and reduce technical debt. We chose a 1:1 design approach, using our React component library that we’ve built and refined over the last five years.
We prepared an AI-assisted migration workflow, which included:
Context engineering and management
Prompt engineering
Defining rules and memory banks so the LLMs understand how we work and generate code our way
Use of Model Context Protocols (MCPs)
Creation of custom AI personas
A strong focus on planning and execution, including writing tests and reviewing code during the approval phase
Rolled out AI tools across the full 10-developer team with fast onboarding and workflow integration
Ran parallel tracks: migrating the system while continuing to build new features
Ensured full compliance and data protection using vetted LLM vendors
Adapted quickly to the AI-enhanced stack. Much faster than the client anticipated

Key results

Up to 60%+ boost in developer efficiency through AI-enhanced workflows
Significant cost savings on migration thanks to reduced manual refactoring
No disruption to ongoing product development
Faster delivery and onboarding of new features
Future-ready architecture for scalable growth

We’ve been working with Protecht since 2011. It’s been a long journey filled with challenges, progress, and big shifts in tech. Through it all, we’ve kept building, adapting, and finding smarter ways forward together.

Tech stack

React, TypeScript,
AI IDE: VS Code + Roo Code,
LLM provider: Requesty,
Most used LLMs: Claude Sonnet 3.7, Claude Sonnet 4, Gemini 2.5 Pro.

Team size

Migration: 2 developers
React Team: 8 developers

AI-native team: All developers work AI-natively, using agentic coding tools (Roo Code, Cline) as standard practice across every Hotovo engagement – enabling faster delivery without sacrificing quality.