AI-driven IT Overhaul
- Customer
- BankDhofar
- Project manager on the customer side
- IT Provider
- Reksoft
- Year of project completion
- 2025
- Project timeline
- February, 2025 - May, 2025
- Project scope
- 2500 man-hours
- Goals
-
The project's primary goal was to define a structured and risk-aware strategy to initiate and accelerate BankDhofar's digital transformation journey from a monolithic IT architecture to a modern microservices-based ecosystem.
The Discovery effort was specifically focused on addressing three key objectives:
- Understanding the bank's current IT integration landscape.
- Designing a modernized target state architecture centered on Apache Camel.
- Building a practical, risk-aware strategy to guide the migration in the smoothest, most efficient, and least disruptive way.
This foundational phase was essential to de-risk the upcoming modernization of the bank’s core architecture and ensure the transformation aligns with broader objectives to enhance agility and support Oman’s Vision 2040 and In-Country Value (ICV) goals.
- Project Results
-
The project successfully delivered all objectives of the Discovery Phase, providing BankDhofar with a clear strategic foundation for its digital transformation.
Key Deliverables and Results
-
System and Integration Registry: A clear inventory of existing systems and integration points, resolving prior documentation gaps.
-
Architecture Vision Document (AVD): A comprehensive set of artifacts detailing the future-state architecture, technical requirements, integration diagrams, and a realistic implementation roadmap.
-
Migration Strategy: A sequenced, resource-aware plan that outlines each step of the transition to microservices.
Key Achievements
-
Gained full transparency into Bank’s legacy IT architecture and integration landscape.
-
Defined a clear and achievable vision for transitioning 71 services and applications to a modern microservices-based integration platform.
-
Created a strong planning foundation with accurately estimated efforts and resources.
-
Implemented a focused pilot to validate Apache Camel-based architecture in a real-world setting before scaling.
-
The uniqueness of the project
The uniqueness of the project lies in its pioneering AI-first approach, making this initiative the first of its kind in Oman’s digital banking sector. Artificial intelligence was integrated as a core element at every stage - from ideation and analysis to testing - ensuring that AI tools underpinned all processes rather than being applied sporadically.
The AI-first approach can deliver more than 40% in resource savings - AI can achieve in hours what might take humans months, provided experts guide it with the right context. This approach significantly accelerated each phase of the project: from analyzing the existing architecture, which spanned more than 70 systems and 1,000 integration flows, to creating a prototype of the target architecture. The AI-first method automated decision-making data generation, optimized resource use, and accelerated development through analytics and machine learning.
- Used software
-
The project leveraged a modern, AI-first technology stack to analyze, design, and plan the migration. The key software and systems used included:
1. Core Integration & Development Framework:
Apache Camel: Selected as the core framework for designing and prototyping the future microservices-based integration architecture.
2. AI & Analytical Tools:
Large Language Models (LLMs), including Retrieval-Augmented Generation (RAG) technology and AI assistants, were deployed to accelerate reverse-engineering of legacy systems, automate code generation (Python), create technical documentation, and analyze system compatibility for migration. A suite of diagnostic and analytical tools was used for the deep-dive assessment of the IT landscape.
- Difficulty of implementation
-
The primary difficulty stemmed from working with limited existing documentation, which required the team to virtually reconstruct the complete picture of the current IT landscape from scratch to ensure all functional and non-functional requirements were fully understood and preserved.
This involved methodically analyzing over 70 systems and 1,000+ integration flows to develop a complete and accurate registry—a crucial foundational step before architectural planning could commence. The team successfully navigated these challenges through the application of advanced AI-powered analysis tools and meticulous validation processes, ultimately delivering a clear and actionable roadmap for the bank's modernization journey.
- Project Description
-
BankDhofar, the Sultanate’s largest bank by branch network size, engaged Reksoft to develop a comprehensive strategy for transitioning to a new IT architecture using an AI-first approach. At the heart of the partnership was a bold initiative to support BankDhofar's migration from a traditional monolithic IT architecture to a microservices-based ecosystem. This shift aimed to enhance agility, scalability, and customer experience, positioning the bank to respond more dynamically to changing market demands and rapidly evolving customer expectations.
The project consisted of a focused two-month Discovery Phase that addressed three fundamental questions: understanding the current integration architecture, designing the future integration architecture, and developing a practical transition strategy. The work was executed in two main stages.
In the first stage, Reksoft conducted a deep analysis of BankDhofar's IT landscape, spanning more than 70 systems and 1,000 integration flows. Using large language models (LLMs), the team reverse-engineered existing integration services and architecture, quickly restoring system logic. Retrieval-Augmented Generation (RAG) technology enabled the analysis of unsupported technologies and automated the creation of technical documentation, producing a complete validated registry of systems and integrations.
In the second stage, specialists designed the target integration architecture centered on Apache Camel. AI assistants automated Python code generation for integration components, data processing routes, and architectural diagrams. Locally deployed LLMs evaluated the compatibility of existing systems with the new architecture, assessing technical complexity and business relevance. This analysis informed a detailed migration roadmap with priorities and risk assessment, complemented by a working prototype that validated the technology stack.
The project laid the groundwork for BankDhofar's long-term competitiveness and digital agility, supporting the bank's commitment to technological leadership while aligning with Oman's Vision 2040 and In-Country Value objectives through local talent development and ecosystem growth.
- Project geography
-
The geographical scope of this project was nationally focused within the Sultanate of Oman.
As a strategic initiative for BankDhofar, one of Oman's largest and most technologically advanced financial institutions, the project was designed to modernize its core IT infrastructure to enhance its services within the national market. Furthermore, the project directly supported Oman's national economic and digital vision by aligning with Oman's Vision 2040 and In-Country Value (ICV) objectives, focusing on local talent development and strengthening the country's digital ecosystem.
While the expertise and technology applied are global, the project's immediate impact and strategic importance are concentrated on enhancing digital banking capabilities within Oman.