Latest videos

How Agentic AI Is Transforming Code Maintenance

Summary This webinar explored the practical impact of Agentic AI on developer productivity, testing, and code maintenance at scale. Moderated by Gautam, the discussion featured insights from Ty Smith, an engineering leader at Uber, and Carlos, a Senior Principal Engineer at Amazon. Together, they examined real-world implementation of AI-assisted development tools, challenges in evaluating and adopting these technologies, and how roles and workflows are evolving in response. Relevant Resources Gitar.ai: https://gitar.ai/ Connect with Ty: https://tysmith.me/ Connect with Carlos: https://www.linkedin.com/in/carlos-arguelles-6352392/ Key Takeaways 1. AI at Scale: Uber’s “Auto Migrate” uses Agentic AI to convert millions of lines of Java to Kotlin—blending deterministic tools, LLMs, and multi-stage verification. 2. LLMs for Testing: At Amazon, natural language tests powered by LLMs outperform traditional frameworks in flexibility and bug discovery, but require strong guardrails. 3. Tool Overload: The rapid evolution of AI dev tools demands nimble evaluation strategies—prioritizing flexibility, optionality, and human-in-the-loop feedback. 4. Measuring ROI: ROI is multi-dimensional—factoring in test creation speed, flakiness, maintenance cost, and “dev years saved,” not just lines of code. 5. Changing Roles: Developers are shifting from coding to orchestrating agent workflows, requiring new team structures and cross-functional thinking. 6. MCP & Governance: Model-Component Protocols (MCPs) are powerful but bring security, auth, and governance challenges that must evolve alongside usage. 7. Experiment with all the AI tools you can get your hands on. Key Timestamps 00:00 – Intro to panelists and topic: Agentic AI & developer productivity 2:11 – Context on challenges post-code-generation (maintenance, security) 5:01 – Uber’s Auto Migrate project: centralizing code transformation 10:23 – Amazon’s use of LLMs for natural language-based test execution 15:17 – Evaluating AI tools, trust issues, and cultural blockers 23:09 – ROI frameworks and balancing dev time vs. hardware cost 27:04 – Changing job roles and future of developer archetypes 34:50 – Code quality and ownership in the age of AI generation 39:57 – Flaky tests and LLM creativity: managing guardrails 46:08 – Scaling AI agents: context size, modularity, and multi-agent systems 51:14 – MCP governance, authentication, and agent policy design 54:03 – Injecting expert agents for accessibility, image quality, etc. 57:00 – Final thoughts and advice for developers navigating the AI shift #AI #AgenticAI #SoftwareEngineering #DeveloperProductivity #CodeMaintenance #Gitar #UberTech #AmazonTech #AIInfrastructure #DevTools #MCP

The State of AI Development Tools: Innovations, Challenges, and the Road Ahead

Watch the full State of AI Development Tools webinar featuring industry experts Daniel Liem (Gentrace.ai) and Gautam Korlam (Gitar.ai) as they dive deep into the evolving landscape of AI-powered software development. This session covers: ✅ The latest AI development tools revolutionizing engineering workflows ✅ Key challenges in AI model reliability, scalability, and deployment ✅ Best practices for automated code refactoring and AI-driven testing ✅ Predictions on where AI in development is headed next 📢 Whether you're a developer, researcher, or AI enthusiast, this webinar offers valuable insights into the tools and strategies shaping the future of AI engineering.

Gitar intro at AWS reInvent 2024

Learn how to eliminate technical debt by using a combination of code analysis and gen AI with Gitar. Visit us at https://www.gitar.ai to learn how our automated software maintenance can help with code and framework migrations, code clean up and more.

How We Automated Code Maintenance and You Can Too!

Let’s face it: as developers, we dedicate a third of our time to code maintenance, which includes tasks such as upgrading dependencies, addressing security vulnerabilities, and removing obsolete code. This is tedious and repetitive. Neglecting regular maintenance can lead to costly outcomes, including unexpected crashes, and it makes the codebase more difficult to understand and evolve. However, automation of these tasks is not always straightforward. Existing tools such as security scanners and feature flag systems warn you about the issues or obsolete code, but fall short of automatically rectifying these problems. Tools that upgrade dependencies merely increase the version number, leaving engineers to handle any API compatibility issues. Automating code changes is hard, and the polyglot nature of modern development makes it harder. In this talk, we delve into code rewriting techniques such as pattern matching, program analysis, and AI. We illustrate how we leveraged the complementing power of these tools to generate over 1,800 automated pull requests, eliminating or refactoring more than 500,000 lines of code. In this talk, you also learn how to harness the power of these tools to drive down tech debt, ensuring your codebase is not only functional but also future-proof. Presented by Ameya Ketkar and Gautam Korlam (Gitar) at DPE Summit 2024, an event developed and hosted by Gradle.

Large Scale Code Refactoring

Join Donald, as he demonstrates how Gitar simplifies refactoring large-scale codebases, using the Confluent CLI application as an example. This massive Go-based project, with over 1,000 files and 100,000 lines of code, faces challenges like feature flag proliferation and technical debt. In this demo, you'll see how Gitar: - Automates the cleanup of a feature flag across an entire codebase. - Performs deep static analysis to identify and clean up all related dead code. - Generates detailed, traceable pull requests for seamless code reviews. - Gitar makes tackling technical debt in large codebases efficient and stress-free. 💡 Learn more and join the conversation at: https://gitar.ai Join our community: https://join.slack.com/t/gitarcommunity/shared_invite/zt-2v9b1j0mt-mrdX5WRUK0txQ8YLkO9TPw Twitter: @GitarCode Website: gitar.ai Transform your codebase with Gitar today! 🚀

Automating the Removal of Lombok Experimental Annotations with GitarBot

Are Lombok experimental annotations creating complexity in your Java codebase? Gitar Bot makes it simple to modernize your code while keeping it clean and maintainable. In this video, Roshan from Gitar demonstrates how our tool can seamlessly remove Lombok experimental annotations, converting them into pure Java code. Whether you're looking to simplify dependencies, improve code readability, or move to better-supported libraries, our solution is designed to save you time and ensure accuracy. What you’ll learn: ✅ Why teams choose to remove Lombok experimental annotations ✅ A step-by-step guide to using Gitar Bot to automate the process ✅ Examples of clean, pure Java code generated by the tool This isn’t just a de-Lombok process—it’s a smarter, more efficient way to ensure your codebase evolves with your team’s needs. Learn more at: https://gitar.ai Join our community: https://join.slack.com/t/gitarcommunity/shared_invite/zt-2v9b1j0mt-mrdX5WRUK0txQ8YLkO9TPw Don’t forget to like, comment, and subscribe to see more ways Gitar can streamline your development workflow! 🚀

Automating your JUnit 4 to JUnit 5 Migration with GitarBot

Migrating your test suite from JUnit 4 to JUnit 5 just got easier! 🚀 In this video, Roshan, demonstrates how our automated tool simplifies the daunting task of migrating JUnit 4 tests to JUnit 5. No more manual updates, potential errors, or wasted weeks of developer time—our Gitar Bot handles everything for you, from updating imports and annotations to modernizing assertion syntax. What you’ll see in this video: ✅ How to install and use Gitar Bot in your repository ✅ A step-by-step walkthrough of the migration process ✅ Examples of updates made to imports, annotations, and assertions ✅ How the tool creates a seamless, error-free pull request If you’re looking to modernize your codebase effortlessly, this video is for you. Say goodbye to manual migrations and hello to automation! Learn more at: https://gitar.ai Join our community: https://join.slack.com/t/gitarcommunity/shared_invite/zt-2v9b1j0mt-mrdX5WRUK0txQ8YLkO9TPw Don't forget to like, comment, and subscribe for more tips on automating code maintenance! 👍

Automating Flutter Code Refactoring

Discover one of Gitar's most powerful features: its ability to work across a wide range of programming languages. In this demo, we showcase how Gitar simplifies code maintenance by cleaning up a Flutter repository to permanently enable a dark mode feature. Using Gitar's GitHub bot, you can: - Automate feature flag cleanups. - Generate clean and optimized pull requests. - Eliminate leftover dead code with ease. Watch as Gitar analyzes Flutter code, refactors it, and creates a pull request, all with just one command. Say goodbye to manual code cleanup and hello to automated efficiency! Learn more at: https://gitar.ai Join our community: https://join.slack.com/t/gitarcommunity/shared_invite/zt-2v9b1j0mt-mrdX5WRUK0txQ8YLkO9TPw Don’t forget to like, comment, and subscribe to see more ways Gitar can streamline your development workflow! 🚀

Webinar: Code migration best practices: Successful strategies for automating code migrations

Replay Gitar's webinar to learn how to transform code migrations from a headache into a smooth, efficient process. We cover best practices, key steps to follow, and how to de-risk timelines with smart automation. You'll walk away with tips on getting executive buy-in, leveraging tools, preventing regressions, and articulating the business value of seamless migrations. Don’t miss out on unlocking a hassle-free migration strategy! Learn more at: https://gitar.ai Join our community: https://join.slack.com/t/gitarcommunity/shared_invite/zt-2v9b1j0mt-mrdX5WRUK0txQ8YLkO9TPw Don’t forget to like, comment, and subscribe to see more ways Gitar can streamline your development workflow! 🚀