The Ruby AI Podcast

Kelly Sutton, CTO and co-founder of Scholarly, builds a faculty information system that secures and automates university workflows. She discusses why higher ed trusts vertical SaaS, how Scholarly uses AI for product surfaces and an admin MCP server, the need for human-in-the-loop checks, and why small, reviewable AI outputs speed adoption and reliability.

Thomas Witt, founder of Vendis.ai and operator at Expedite Ventures, builds AI-native CRMs and AI-heavy production systems. He explains why conversation-first CRMs replace rigid forms. He discusses using Ruby on Rails with Hotwire, DynamoDB, async Ruby, vector search, and multi-model LLM workflows. He also covers telemetry for prompt chains and how small teams can be amplified by AI.

Kinsey Durham Grace, a member of GitHub’s coding agent core team and active Ruby speaker, explains Agent HQ and agent workflows. They discuss AI-generated artwork, using custom agents and Codespaces, making agents modular and transparent, and how observability, intent capture, and repo artifacts shape future developer workflows.

Ben Schofield, author and longtime Ruby contributor who studies expertise and staff engineering, joins to talk agentic development. They explore when to use agents versus coding, how to train engineers for staff roles, and the role of intentional defaults and context in tooling. Short, practical takes on learning breadth, specialization, and using AI to practice influence and specification skills.

They celebrate Ruby turning 30 and a quiet Ruby 4 release, then dig into performance, concurrency, and new packaging challenges. The conversation explores AI tooling for coding, agent-driven workflows, and the costs of AI “slop.” They debate open source sustainability, marketplace fragmentation, and wishes for better Ruby tooling and persona-based code helpers.

Evan Phoenix, a veteran Ruby programmer and CEO of Mirren, shares insights on the evolving role of AI in software development. He distinguishes between real and fake AI, emphasizing AI as an implementation detail rather than just a product. The discussion delves into the impact of AI on engineering practices, such as performance optimization and human-centric design. Evan envisions a future where agents simplify coding and prediction while enhancing experimentation. He also predicts a resurgence of monolithic architectures as integration costs decline.

Chris Hasinski, an AI and Ruby expert with a machine learning background from UC Davis, shares impactful insights into self-hosting AI models. He discusses the benefits of control and cost savings, along with challenges like latency. Chris recounts his ML journey, covering applications beyond text and fine-tuning techniques. He highlights Ruby's potential in ML, the importance of quality data, and nuances of local model performance. With insights into monitoring and developer experience, his vision includes enhancing Ruby's role in the evolving AI landscape.

Carmine Paolino, a developer and creator of the Ruby LLM project, delves into the rapid success of Ruby LLM, driven by his philosophy of simplicity and adaptability. He discusses innovative topics like progressive disclosure in APIs, multi-agent systems, and context management to enhance efficiency. Notably, he emphasizes the importance of flexible library design and practical applications, alongside tackling challenges in concurrency using Async. Carmine's insights will inspire Ruby developers to leverage AI tools more effectively.

In this discussion, Avi Flombaum, founder of Flatiron School, shares insights on teaching programming and the evolving impact of AI on software development. He emphasizes the importance of product thinking alongside coding skills and advocates for using AI as a powerful tool in the learning process. Avi reveals how integrating AI can enhance developer workflows and increase output efficiency. He also discusses the need for a modern curriculum that deeply engages students, promoting problem-solving and practical challenges to prepare them for real-world scenarios.

In this episode of the Ruby AI Podcast, co-hosts Valentino Stoll and Joe Leo engage in a lively discussion with guest Justin Searls. They explore the evolving landscape of software development with agentic AI tools, comparing traditional agile methodologies with emerging AI-driven practices. Justin Searls his experiences with refactoring and the challenges of integrating AI tools into development workflows. The conversation touches on the suitability of AI in coding, philosophical perspectives on reinforcing proper software practices, and the future potential of these technologies. Justin also provides valuable insights on configuring AI tools for better productivity and discusses his personal coping strategies with the frustrations of modern AI capabilities.00:00 Introduction and Hosts Banter00:30 Guest Introduction: Justin Searls03:13 Justin's Career and Conference Talks07:52 The Evolution of Agile and Development Practices16:07 Challenges with AI and Iterative Development27:47 Recalibrating Development Processes28:00 Adoption of Pivotal Labs' Methods28:28 Continuous Integration and Testing29:21 AI in Development: Current State and Challenges30:16 The Role of AI Agents in Development32:17 Frustrations with AI Tools35:03 Philosophical Reflections on AI in Development36:16 Generative vs. Subtractive AI37:06 The Future of AI in Software Development39:27 Balancing Coding Enjoyment and Productivity44:02 Capability vs. Suitability in AI Tools46:35 Prompt Engineering Tips and Tricks52:39 Closing Thoughts and Plugs