Migrating from COBOL with AI: A Moonshot Demo
-
Julia Kordick
Microsoft
Global Black Belt - Developer Productivity
This talk presents an approach that utilizes static code analysis using Konveyor.io (CNCF Sandbox project) coupled with Large Language Models (LLMs) to facilitate automated code transformation. Our method comes from the tool โKaiโ, which analyzes static code to pinpoint areas within source code requiring modification. Kai uses the power of LLMs to generate code changes to resolve identified incidents. It eliminates the need for fine-tuning LLMs. Instead, it augments the knowledge of LLMs with Konveyor data through prompt engineering (few shots) and the use of Retrieval-Augmented Generation (RAG). This session includes a demo showcasing how a legacy application is migrated and then deployed to Kubernetes using the power of Kai.
World Congress 2025
Julia Kordick
Microsoft
Global Black Belt - Developer Productivity
Damir
daenet
Lead Sofwtare Architect
Gregor Schumacher
Riverty
Tech Lead Innovation
Marcel Gocke
Riverty, Senior Architect
Sujay Joshy
Riverty
AI Engineer
Daniel Oh
Red Hat
Sr. Principal Developer Advocate