The Ruby AI Podcast

In this episode of the Ruby AI Podcast, host Valentino Stoll talks with special guest Kieran, a prominent figure in the Ruby AI space. Kieran recently gave a talk at the San Francisco Ruby Meetup about his new gem, Leva, which focuses on LLM evaluations in Ruby. Kieran discusses his background, his passion for AI and Ruby, as well as his journey in building AI products, including his tool Cora, which helps manage email inboxes by categorizing and summarizing emails using AI. Together, Valentino and Kieran explore the process, challenges, and best practices of creating AI-driven gems and tools in Ruby, the importance of evaluations, and the fun and creative aspects of integrating AI into Ruby on Rails projects.Mentioned in the show:Kieran Klaassen – Ruby developer, creator of Cora and Leva.Leva gem – Kieran's LLM evaluation framework for Rails.Jumpstart Pro – “is the best Ruby on Rails SaaS template out there”.Stepper / Stepper Motor (workflow engine) – a “journey” with steps for background jobs.Jaccard Index – A metric for set similarity (|A∩B|/|A∪B|).LangSmith – a platform for building production-grade LLM applications.Morph LLM – The Fastest Way to Apply AI Edits (4500+ tokens/sec).Friday AI Agent – An AI-powered coding agent that handles PRs from start to finish.DSPy.rb – Framework for building AI agents and optimizing prompts.Highlights:00:00 Introduction and Guest Welcome00:53 Kieran's Background and AI Journey01:20 Building AI Tools and the Leva Gem03:47 Challenges and Best Practices in AI Development07:16 Evaluations and Real-World Applications07:36 Community Recognition and Adoption12:37 Prompt Engineering and Model Testing22:06 Leveraging AI for Workflow Optimization28:35 Visualizing Workflows and Tools31:44 Exploring Hybrid Orchestration Layers33:15 Debating Deterministic Workflows vs. Agent Flows34:28 The Fun of Experimenting with AI and Ruby34:55 Building Gems and Learning Through Creation40:03 The Value of Rails in AI Development46:28 Evaluating AI Outputs and Metrics50:40 Annotation and Continuous Improvement53:50 Future of AI and Rails Integration54:54 Closing Thoughts and Recommendations

Obie Fernandez, a Ruby expert and Shopify Principal Engineer with 20 years of experience, joins Valentino Stoll and Joe Leo for an engaging discussion. They delve into the launch of Roast, an open-source Ruby framework for AI workflows. Key topics include innovative AI orchestration, the evolution of AI in coding practices, and the interplay between creativity and software development. Obie highlights the importance of effective prompting, navigating knowledge silos in AI, and the transformative potential of AI in both music production and tech.

Justin Bowen, a Ruby developer with 17 years of experience, shares insights about Active Agent, his innovative Rails-native framework for integrating AI. He discusses challenges in shipping AI, emphasizing the importance of context and real-world testing. Bowen also critiques the hype around AI, comparing it to crypto trends. The conversation explores the balance between open-source sustainability and monetization, community involvement, and the evolution of Ruby in the AI landscape, while highlighting exciting projects like Osmo AI and the upcoming Ruby AI hackathon.

Scott Werner, an author and creator of the Sublayer AI-agent framework, dives into the evolving landscape of AI in the Ruby community. He discusses the innovative 'generators + actions' structure of Sublayer and the quirky Monkey’s Paw framework that turns Markdown wishes into web pages. The conversation also explores the tension between AI and human input in development, particularly the challenges of AI code generation. Plus, Scott emphasizes how community engagement fuels creativity while adapting to the rapid changes AI brings to the coding process.

The hosts dive into the vibrant Ruby AI community, revealing exciting projects like Phoenix that enhance software development. They discuss the challenges and unique advantages Ruby presents for AI integration, contrasting it with other languages. The conversation shifts to the overlooked potential of AI beyond chatbots, emphasizing the need for adaptability in coding practices. Listeners will learn about measuring side effects in interconnected systems and how emerging tools can lead to creative solutions in the evolving landscape of AI-powered applications.

In this episode of the Ruby AI podcast, hosts Landon and Valentino discuss the exciting developments in the Ruby AI community. They explore three key gems: Ruby OpenAI, Raix, and Langchain.rb, highlighting their features, use cases, and the importance of evaluation methodologies like RAGAS in AI systems. The conversation emphasizes the collaborative spirit of the Ruby AI community and the potential for innovation in AI applications using Ruby.TakeawaysThe Ruby AI community is vibrant and growing.Ruby OpenAI is essential for integrating OpenAI's capabilities.Raix gem offers an object-oriented approach to AI in Ruby.Langchain RB normalizes AI provider integrations in Ruby.RAGAS provides a framework for evaluating AI outputs.Community engagement is crucial for Ruby AI's growth.Documentation is key for developers using these gems.Collaboration among developers enhances innovation.AI systems require robust evaluation methodologies.Ruby is at the forefront of AI development.Sound Bites"This is gonna be really exciting.""Join the Ruby AI Builders Discord.""There's so much cool stuff out there."