Exploring Active Agent, or can we build AI features the Rails way?—Martian Chronicles, Evil Martians’ team blog

In a fast-paced world with AI oozing out of every pore, frameworks and ecosystems must adjust quickly to rapidly evolving business demands. Everyone needs smart features in their apps. The easier it is to add AI-driven features to the project built with Some Framework, the more likely it will be the tool of choice. Let’s assume that “Some Framework” is “Ruby on Rails” and explore this ecosystem’s AI readiness! The Ruby and Rails AI ecosystem took off as soon as the AI revolution sparked. It evolved from unofficial LLM provider SDKs like ruby-openai to specialized libraries such as Raix and RubyLLM. Each offers different approaches to integrating large language models into Ruby applications, but neither feels like a missing Rails abstraction for AI to me. I prefer abstractions that follow Rails conventions and design principles and bring a familiar user experience. Both Raix and RubyLLM focus on providing a common interface for chatting with AI (and they do that very well), but do not go above that (in the layered architecture sense, they cover mainly the infrastructure layer).