Agents aren't magic. They're LLMs that can call your code. RubyLLM 1.12 adds a clean DSL to define and reuse them.

The RubyLA blog offers insights, tutorials, and community updates for Ruby developers in Los Angeles and beyond. Developers can explore Ruby language features, web development frameworks, and best practices for building Ruby applications. Additionally, the blog covers Ruby meetups, events, and job opportunities in the Los Angeles area, fostering collaboration and networking within the local Ruby community.

RUBYLAND

RubyLLM 1.12 introduces a DSL for defining reusable AI agents as Ruby classes. Agents are demystified as LLMs with tool-calling capabilities—no orchestration frameworks needed. The release adds an Agent base class with macros for model configuration, instructions, tools, and temperature, supporting lazy evaluation for runtime context. Rails integration enables prompt conventions via ERB templates and persisted chat sessions. The update also includes AWS Bedrock full coverage via Converse API, Azure Foundry API support, and clearer instruction semantics.

RubyLLM 1.12: Agents Are Just LLMs with Tools