From Legacy to Cloud Native: Transforming Applications with Konveyor AI
summary
Konveyor ships Kai, a VS Code extension that uses RAG with user-supplied LLMs to generate and iterate actual code patches, re-running the analyzer and compile/tests until issues are fixed. The project already exposes over 2,400 analyzer rules and supports Java, .NET, Go, TypeScript and Python, with a 0.1 VS Code release in March. Detections map to concrete patch suggestions, tracked as accepted solutions to improve subsequent suggestions.
AI-written summary · about
chapters (13)
- 0:00Konveyor AI introduction
- 2:26Konveyor components overview
- 5:15Application analysis in UI
- 7:25Rules and issue detection
- 10:14Analyzer engine reports
- 12:44Human migration limits
- 13:24Konveyor AI automated fixes
- 15:51RAG and AI integration
- 17:57Agentic workflow validation
- 20:43Prompt structure learning
- 23:34VS Code demo
- 25:43Java to Quarkus migration
- 26:48Conclusion
related talks
38mModernization 101: A Beginner's Guide to Application Modernization and Methodology
35mGoing Beyond Copilot with AI Agents
22mIncreasing developer productivity with Generative AI
44mWe Hate Code: The !Joy of Maintaining Dead Code
16mEmpower your organization with production-ready RAG apps on Azure
26mDetecting and Mapping Code Defects Introduced by Generative AI Using CodeLogic & Neo4j
47mExploring a complex codebase with AI
16mSewing up success even when RAGs unravel