Open Mainframe Project Summer Mentorship Series: Midterm Updates – At this midpoint, our selected mentees are reporting in. Below, you’ll learn what they’ve built, the challenges they’ve overcome, and their goals for the rest of the summer. We’re proud of every contribution and eager to see what comes next. Hear from Anshu Saini, Indian Institute Of Information Technology, Design and Manufacturing, Kancheepuram, India.
My Background and why I chose this project
I’m a final year B.Tech student in Computer Science and Engineering, majoring in Artificial Intelligence at Indian Institute Of Information Technology, Design and Manufacturing, Kancheepuram, India.
My technical journey has been deeply rooted in AI — from developing various projects or applications in the healthcare sector to real-time AI surveillance systems. While these projects sharpened my skills in deep learning and system-level thinking, I was increasingly drawn to legacy transformation—where AI doesn’t just optimize but redefines the foundations of enterprise software.
Mainframe modernization through AI struck me as the perfect convergence of innovation and impact. It isn’t just about making code better—it’s about bringing agility to critical infrastructures in finance, healthcare, and public systems that millions rely on.
Importance of AI in Modernizing Mainframes
Mainframes still handle essential services worldwide, often written in aging languages like COBOL or PL/I. These systems are stable—but not scalable in the cloud-native, agile-first world. Manual migration is costly, slow, and risky. AI changes this equation by automating code transformation and providing intelligent insights into system restructuring.
Our white paper aims to fill a significant knowledge gap: offering a structured, evaluative guide to using AI-based tools for mainframe modernization. Rather than simply listing tools, we propose a comparative, KPI-driven framework that stakeholders can use to choose the best-fit solutions for their environments.
Work done so far
Over the past few weeks, my work has focused on three major components
3.1. Foundational Research & Landscape Mapping:
Explored current AI tools in code transformation, such as IBM WatsonX, Microsoft Copilot, AWS Blu Age,Google Gemini,etc. The focus was on identifying differentiating factors like IDE integration, scalability,AI traceability and many more.
3.2. Drafted Evaluation Criteria and KPIs:
Developed a structured framework using Key Performance Indicators (KPIs), including:
• Language compatibility
• AI automation
• CI/CD & IDE integration
• Refactoring safety
• Cost-effectiveness, etc.
* Created a scoring methodology to quantitatively benchmark tools.
3.3. Interviewed Expert:
Conducted an interview with Mr. Eric Herness (currently a Kyndryl fellow,VP and Cloud Chief Architect and he has also been with IBM for 36 years as a Hybrid Cloud CTO and CTO of IBM Cloud Engagement Hub) and Mr. Steven Dickens (CEO and principal analyst at HyperFrame Research) to capture insights around enterprise needs, tool selection metrics, and lessons from their past modernization projects.
3.4. Visual Representations:
Designed radar charts, heatmaps, and flow diagrams to support stakeholder decision-making.
What’s Next
As the project enters its second half , the roadmap ahead includes:
- Interviewing more experts to expand insights
- Refining the draft white paper with reviews from my mentor , peers and experts.
- Finalizing the paper with an optimized scoring methodology , decision trees and visualization to help the customers and vendors easily access or choose tools based on their requirements.
This mentorship has given me an opportunity not just to contribute, but to learn deeply—about how legacy meets AI, and how modernizing infrastructure is as much about strategic design as it is about intelligent automation. I’m excited to deliver a comprehensive, useful, and forward-thinking guide by the end of this journey.
