Over the past years, we have infused AI and advanced data science techniques into various aspects of cybersecurity at ING, a large European bank with over 60,000 employees. In this talk, we will present the lessons learnt from applying AI-driven solutions to critical areas within CISO, namely Vulnerability Management, Secret Leakage Prevention, Identity and Access Management, and Data Leakage Prevention. The shift towards AI-based approaches was not just about automating tasks but about enhancing the quality of security decisions, removing unnecessary access, reducing false positives, and optimising the workload for Security Operations Centre (SOC) teams. We will reflect on the key challenges we encountered, the most successful methodologies, and the tangible improvements we have observed in managing and defending a complex banking infrastructure. This presentation aims to share with the audience not just the technical achievements but also the practical steps we took to make these innovations work in a real-world corporate environment. Our talk will cover the intersection of AI with traditional cybersecurity methods, the tools and frameworks that yielded the most benefits, and the areas where we believe future work can push AI even further. We will show how coupling vulnerability data to our alerts helped significantly reduce the number of false positives for our SOC analysts and the impact our methods had on Role Access Optimisation, Secret Leakage Prevention, and Data Leakage Detection capabilities. Attendees will leave with an understanding of what has worked, what hasn't, and how AI can be a force multiplier in their organisations' cybersecurity frameworks.