> Markdown version of [/videos/959-supercharging-static-code-analysis-konveyor-ai-llms](https://www.wearedevelopers.com/videos/959-supercharging-static-code-analysis-konveyor-ai-llms). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Supercharging Static Code Analysis: Konveyor AI & LLMs

What if you could automate legacy migrations without hitting LLM token limits? Discover how Konveyor AI combines static analysis and RAG to safely refactor monolithic codebases.

- **Speakers:** [Daniel Oh](https://www.wearedevelopers.com/@daniel-oh)
- **Event:** World Congress 2024
- **Published:** August 20, 2024
- **Duration:** 33:14
- **URL:** https://www.wearedevelopers.com/videos/959-supercharging-static-code-analysis-konveyor-ai-llms

## Summary

Application modernization—such as migrating monolithic architectures to cloud-native microservices—presents significant development bottlenecks when relying on manual refactoring, generalized AI queries, and fragmented documentation. To achieve better reliability, scalability, and security, engineering teams require tools that directly address the complexities of replatforming without relying on isolated code examples or trial-and-error methodologies.

The CNCF open-source project Konveyor AI (Kai) bridges the gap between static code analysis and generative AI workflows to automate these migrations. By combining rule-based static analysis with large language models via a retrieval-augmented generation (RAG) architecture, Konveyor identifies specific legacy syntax issues across an entire repository. Instead of sending the full codebase and exceeding maximum token limits, the tool stores previously solved patterns in a local PostgreSQL database, transparently augmenting prompts to deliver highly accurate, contextual code snippets.

Integrated directly into developer environments like VS Code, Konveyor AI allows engineers to evaluate "as-is" and "to-be" source code side-by-side, accelerating acceptance for major framework changes—like replacing obsolete messaging protocols with reactive patterns. Unlike generalized AI assistants, this solution scales across multiple interconnected repositories, supports customized rules for proprietary frameworks, and builds organizational context over time without incurring the heavy computational costs of custom model fine-tuning.

**Keywords:** application modernization, static code analysis, generative AI refactoring, retrieval-augmented generation RAG, monolith to microservices migration, automated code refactoring, LLM context window optimization, cloud-native application development, custom static analysis rules, repository-wide code analysis, CNCF open-source projects, java EE modernization, local LLM deployments, weblogic to quarkus replatforming

## Chapters

1. **Challenges in traditional application modernization** (00:10) — Traditional application modernization methods often trap developers in frustrating cycles of trial and error using basic search and generic AI tools.
1. **Key drivers and benefits of modernizing applications** (02:33) — Modernization improves codebase security, enhances cloud reliability, scales efficiently, and optimizes workloads for modern infrastructure.
1. **Defining application modernization through the Konveyor project** (04:19) — The Konveyor open-source CNCF project identifies modernization as upgrading CI/CD pipelines, restructuring monolithic data, and expanding service automation.
1. **Evaluating core strategies for application migration** (05:31) — Organizations can navigate cloud migration by choosing from six distinct strategies including rehosting, replatforming, refactoring, and repurchasing.
1. **Addressing refactoring challenges with AI tools** (07:42) — Developers can overcome complicated refactoring tasks by adopting API-driven development and implementing AI analysis modules.
1. **Applying customizable rules for static code analysis** (09:09) — The Konveyor project uses extensible rule sets to analyze artifacts and source code alignments against target cloud environments.
1. **Accelerating code generation with Konveyor AI** (11:29) — Konveyor AI connects to local or remote large language models to deliver precise code snippets and direct solutions for modernization errors.
1. **Setting up Konveyor AI and PostgreSQL locally** (14:14) — Running a local AI server alongside a PostgreSQL database virtual environment prepares the system to catalog code migration solutions.
1. **Configuring the Konveyor AI extension in Visual Studio Code** (16:24) — The IDE extension scans legacy Java applications and evaluates custom configuration rules to identify potential refactoring issues for target cloud runtimes.
1. **Enhancing code suggestions with retrieval-augmented generation** (19:25) — Konveyor AI leverages retrieval-augmented generation to bypass token limits and reuse previously validated fixes to augment new prompts.
1. **Reviewing and accepting AI recommendations in the IDE** (24:38) — Developers can easily inspect side-by-side file differences generated by the AI model to quickly update old namespaces and reactive messaging setups.
1. **Running the modernized Quarkus application with test containers** (28:54) — Deploying the refactored retail microservice showcases how the modernized environment seamlessly connects to a local containerized Postgres instance.
1. **Comparing Konveyor AI to automated coding assistants** (31:46) — Unlike standard coding copilots, Konveyor AI operates across entire organizational repositories to share custom refactoring configurations between developer teams.

## Related Moments

- [Combining static analysis with generative AI](https://www.wearedevelopers.com/videos/1605-navigating-application-modernization-leveraging-gen-ai) (from "Navigating Application Modernization - Leveraging Gen-AI")
- [Open source static code analysis with Conveyor](https://www.wearedevelopers.com/videos/1605-navigating-application-modernization-leveraging-gen-ai) (from "Navigating Application Modernization - Leveraging Gen-AI")
- [Migrating legacy applications using generative AI](https://www.wearedevelopers.com/videos/1605-navigating-application-modernization-leveraging-gen-ai) (from "Navigating Application Modernization - Leveraging Gen-AI")
- [Shifting developer workloads and realistic AI productivity gains](https://www.wearedevelopers.com/videos/1830-wearedevelopers-live-speculaitions) (from "WeAreDevelopers LIVE - SpeculAItions")
- [Modernizing legacy code repositories for robust artificial intelligence](https://www.wearedevelopers.com/videos/100010-ship-smarter-agents-not-bigger-prompts) (from "Ship Smarter Agents, Not Bigger Prompts")
- [Analyzing cloud-based AI code completion architectures](https://www.wearedevelopers.com/videos/961-beyond-autocomplete-local-ai-code-completion-demystified) (from "Beyond Autocomplete: Local AI Code Completion Demystified")

## Related Articles

- [Exploring AI: Opportunities and Risks for Developers](https://www.wearedevelopers.com/magazine/522-exploring-ai-opportunities-and-risks-for-developers)
- [Transforming Software Development: The Role of AI and Developer Tools](https://www.wearedevelopers.com/magazine/527-transforming-software-development-the-role-of-ai-and-developer-tools)
- [13 AI Tools for Developers](https://www.wearedevelopers.com/magazine/302-13-ai-tools-for-developers)
- [MLOps And AI Driven Development](https://www.wearedevelopers.com/magazine/82-mlops-and-ai-driven-development)

## Related Jobs

- [Staff Developer Advocate, GitHub Security Lab](https://www.wearedevelopers.com/jobs/ext/1921051-staff-developer-advocate-github-security-lab) at **GitHub**
- [AI Software Engineer (Germany)](https://www.wearedevelopers.com/jobs/48317-ai-software-engineer-germany) at **Sunhat**
- [Principal Software Engineer, Enterprise AI Platform](https://www.wearedevelopers.com/jobs/ext/1467292-principal-software-engineer-enterprise-ai-platform) at **GitHub**
- [Senior Engineer, Infrastructure Platform](https://www.wearedevelopers.com/jobs/ext/328836-senior-engineer-infrastructure-platform) at **Intercom, Inc.**
- [Staff Software Engineer, Copilot Experiences](https://www.wearedevelopers.com/jobs/ext/164361-staff-software-engineer-copilot-experiences) at **GitHub**
- [Senior AI Agent Software Engineer (Go, Python) (m/f/x)](https://www.wearedevelopers.com/jobs/48277-senior-ai-agent-software-engineer-go-python-m-f-x) at **Dynatrace**