How to use AI in application modernization
Application modernization is often time-consuming and costly, but SUE's latest Tech Talk explores how AI can revolutionize this process. Experts Bob Merkus and Jeroen van Nieuwenhuizen discussed how Large Language Models (LLMs), Retrieval Augmented Generation (RAG), and Agentic AI can streamline modernization by effectively addressing legacy infrastructure and skills gaps.
Recap TechTalk November 2024: How to use AI in application modernization
Historically, application modernization has often been time-consuming and costly. But new technologies also create new opportunities. At SUE, we are innovators at heart. When Generative AI made its breakthrough, we were immediately curious about how we could apply this technology to help our customers innovate faster in their businesses. One of the ways we did this was by looking at the use of AI in application modernization projects.
During our latest TechTalk, our AI and Application Modernization experts, Bob Merkus and Jeroen van Nieuwenhuizen, shared their vision, expertise, and experience.
Common challenges in application modernization
Jeroen kicked off TechTalk by sharing the most common challenges he encounters at many organizations. There are several, but they often involve:
- Dependencies on legacy infrastructure
- A skills gap
- The complexity of legacy code
- The risk of business disruption
These challenges can often be solved by many people, with a lot of time and a large budget. According to Gartner, typical modernization projects take an average of 16 months and cost around $1.5 million. More than a quarter of projects take two years or longer, and 93% of respondents in a recent survey described their modernization experience as "extremely" or "somewhat challenging."
So if application modernization is time-consuming and costly, how can AI help solve these challenges? That's what Bob talked about next.
The Impact of AI on Application Modernization
In this talk, Bob provided a clear and in-depth overview of the role of AI in modernizing applications. After introducing the AI landscape, he delved deeper into Large Language Models (LLMs) and Retrieval Augmented Generation (RAG). He explained how these technologies can significantly influence application modernization by improving information access and providing relevant insights.
He then introduced the concept of Agentic AI approaches: specialized actors, powered by LLMs, that can dynamically interact with their environment by accessing information and performing predefined actions via tool calls. According to Bob, these agentic capabilities make it possible to support application migration and modernization processes more efficiently.
Finally, Bob introduced Re:App, a new AI-driven tool from SUE designed to streamline the replatforming of applications to cloud-native environments. A live demo showed how Re:App can simplify and significantly accelerate the replatforming process.
