Obie Fernandez
BIO
Obie Fernandez began his career as a professional programmer in the early ’90s. From Java to Ruby, Lean Startup, Serverless, and now AI, Obie’s expertise and forward-thinking attitude has consistently placed him on the bleeding edge of innovation. As the author of “The Rails Way,” his contributions to the Ruby on Rails community are widely recognized and respected. Obie’s role as CTO on the founding team of Andela, along with successful entrepreneurial exits, underscores his leadership and business acumen. His latest venture, Olympia, provides AI-powered virtual consulting.
TITLE
Patterns of Application Development Using AI
ABSTRACT
Taking advantage of AI components can transform an application developer’s workflow into an incredibly potent force, capable of competing at an unprecedented scale. This presentation draws on practical real-world experience gained by the presenter over the last 12 months of developing Olympia.chat. We will explore practical approaches ranging from real-time data analysis to automated customer support. The emphasis is on new approaches that let application developers focus more than ever on innovation and creativity.
Attendees will leave with a roadmap for integrating AI tools and techniques into their projects, insights into the potential pitfalls and best practices, and inspiration to explore the boundaries of what a single developer or a small team can achieve with the right tools. The presenter is a well-known Ruby on Rails expert and his latest book, “Patterns of Application Development Using AI” is the definitive tome on the subject.
INTERVIEW
What inspired you to delve into AI and pursue a career in this field?
I’ve benefited greatly in my career from spotting disruptive innovations and jumping in head-first, early. Java in ‘96, Ruby on Rails in ‘05, Serverless in ‘14, and now AI (2019). My first foray into AI unfortunately went nowhere. The problem my team and I were trying to tackle—ultra accurate classification and evaluation of music—was and stlll is an incredibly difficult challenge. But it helped me be in a position to recognize the potential of GPT-3 almost immediately when I saw what it was capable of doing.
What do you see as the most significant challenges in deploying AI in production, and how do you suggest overcoming them?
I’ve been working on general humanized AI assistants for over a year now and I think we’re still a little bit too early in the lifecycle for the truly disruptive and life-changing agentic applications to emerge. GPT-4 is not quite intelligent enough, and certainly not cheap enough to just throw millions of tokens at the problem. There’s not really any effective way to overcome that particular hurdle at the moment, but I think we’re close to surpassing it. Perhaps later this year with GPT-5?
How do you stay updated with the rapid advancements in AI technology, and what resources would you recommend to others in the field?
It’s nearly impossible to keep up. For the most part I just depend on scanning Hacker News once or twice a day. The crowd there generally picks up on the most significant news of the day (and tears it apart in the comments.) Very effective.
What future trends in AI are you most excited about, and how do you believe they will shape the industry?
It’s clear that the emergence of personal AI agents will “change everything” in the same way that the Internet changed everything. Pondering what exactly will happen and how I can personally contribute to it via my startup Olympia keeps me up at night.
What advice would you give to product teams and developers just starting with AI projects?
Definitely to go buy my book Patterns of Application Development Using AI right now! Seriously, I don’t think there’s another resource at the moment that gives you a better onramp to leveraging AI in your software projects. It's over 300 pages of practical material distilled from hands-on experience.