Mashreq has initiated an IBM Bob pilot to test agentic artificial intelligence tools across its software integration engineering operations. The trial examines how autonomous AI agents can support developers, speed up delivery cycles, and assist during software creation and production troubleshooting.
According to reported data from the initiative, the institution achieved a 60% to 70% reduction in time spent on integration design and system troubleshooting. Tasks that previously required two to three hours of manual work were completed within minutes during the tests.
Early Results of the IBM Bob Pilot
The financial institution currently runs an integration platform handling an average of 650 transactions per second across digital channels and payments. Specifically, engineers are evaluating how autonomous systems can assist with solution design, code reviews, and operational maintenance across critical systems.
Mohamed Abdel Razek, Group Head of Technology, Transformation and Information at Mashreq, discussed the engineering direction during the deployment.
“As we continue to advance our digital-first strategy, we are investing in technologies that help our engineering teams move faster while maintaining the resilience and quality our customers expect. Through our pilot with IBM Bob, we’re seeing how agentic AI can help simplify complex integration engineering, accelerate delivery and improve developer productivity.”
Mohamed Abdel Razek, Group Head of Technology, Transformation and Information, Mashreq
Modernizing Architecture with Cloud Technologies
Mashreq is working alongside IBM and Gulf Business Machines to modernize the core integration infrastructure supporting its digital services. The bank uses technologies such as Red Hat OpenShift, IBM Cloud Pak for Integration, IBM MQ, IBM App Connect, IBM API Connect, and Confluent.
These software components provide a foundation designed to maintain stable data flow, API connections, and regulatory compliance across international markets. In addition, the organization evaluates how fintech systems handle multi-country transaction requirements.
Context Forge and Gateway Operations
To support AI agent workflows, Mashreq implemented IBM Context Forge based on the Model Context Protocol. This architecture grants autonomous tools controlled access to enterprise integration standards, system documentation, and operational context.
Furthermore, a dedicated gateway handles approximately 4,000 requests each month from AI agents to connected core banking, payments, and enterprise applications. Santosh Vaidya, Head of Payments and Digital Services at Mashreq, stated that the tool supplies the technical context engineers use daily for architectural decisions.
“The next chapter of AI will require empowering developers and engineers with intelligent agents that can collaborate across complex software engineering workflows.”
Shukri Eid, VP & General Manager, IBM Gulf Levant and Pakistan, IBM
Future Deployment Plans
Technical leaders are also examining an on-premises deployment of the platform to serve mission-critical applications that demand strictly local computing resources. Consequently, this configuration will help fulfill regional regulatory requirements and local data residency rules in banking jurisdictions.
By expanding the scope of the IBM Bob pilot, Mashreq intends to prepare its software systems for automated, agent-supported banking operations. Moreover, the trial establishes practical benchmarks for measuring developer efficiency and platform stability in real-world banking environments.
