AI agents to improve observability and achieve self-healing in banking IT

Innovaway is preparing to structure concrete use cases for the integration of Agentic AI in three strategic areas.

“The first – says Antonio Burinato, General Manager of Innovaway – concerns the observability of systems, an evolution of current process monitoring, typically siloed, towards end-to-end predictive capabilities: AI agents can automatically connect performance in infrastructures and application ecosystems to processes, identifying bottlenecks and performance anomalies before they impact business continuity and customers.”

Proactive incident management

The second area supports a “prevention and act” approach, where AI agents enable proactive incident management.

By analyzing historical patterns, real-time metrics, and cross-system correlations, AI can predict, for example, potential failures in instant payment systems, blocks in KYC/AML procedures, or resource saturation during peak periods, automatically triggering corrective actions before problems arise.

Agentic AI for operational management

The third area “concerns Agentic AI, which can also improve operational management on open unstructured sources, processing and contextualizing information, for example from application logs, incident management tickets or continuously evolving documentation – to extract insights and accelerate decisions and interventions,” continues Burinato.

Human supervision remains central

Innovaway’s roadmap includes orchestration of multiple specialized AI agents that collaborate to complete and verify complex tasks, overcoming the limits of a single AI model and creating scalable, efficient systems for interconnected workflows.

All this without neglecting human supervision and decision-making.

“This development – continues Burinato – will begin in 2026 to respond to the growing infrastructural complexity of enterprises linked to digital transformation – hybrid multi-cloud environments, increasing data volumes, regulations, and cybersecurity risks – with the need for faster response times.”

From Break-Fix to Predict and Prevent

“For decades, the world of IT services has been dominated by a reactive paradigm, known as 'Break-Fix' – continues Burinato. A model based on tickets, fragmented workflows and consequent user frustration, where success was measured by the speed of resolving an already manifested problem. Today, this approach is not only inefficient but has become a brake on business. And the answer to this challenge comes from technology.”

Banks must move from reaction to prediction and prevention, anticipating and resolving issues before impact thanks to AI-driven automation.

“The truly transformative approach consists in using platforms natively designed with Agentic AI at the center – emphasizes Burinato. As confirmed by analysts like Gartner and McKinsey, 'AI Agents' are the next frontier: systems capable of performing complex multi-step tasks without direct human supervision. Applied to IT service management, Agentic AI does not just suggest a solution: it executes it. This allows for the creation of true 'Self-Healing' ecosystems.”

The Benefits

AI Agents offer significant advantages for banks: reducing operational costs (TCO), minimizing downtime, increasing efficiency, and boosting compliance readiness.

“Banks can thus make a qualitative leap also in terms of compliance, reaching new standards of resilience and adaptability – concludes Burinato. The IT infrastructure thus becomes more robust and reactive, capable of automatically managing any critical issues without service interruptions, in line with what is required, for example, by the DORA regulation.”