What problem does it solve?
This Skill solves the problem of building reliable, maintainable LLM-powered features in Ruby applications by replacing fragile prompt strings with type-safe signatures, modular components, and automated optimization.
Core Features & Use Cases
- Type-Safe Signatures: Define LLM inputs and outputs using Sorbet types, enums, and structs for compile-time safety and reliable structured outputs.
- Modular Agents & Tools: Compose ReAct and CodeAct agents with type-safe tools, lifecycle callbacks, and fiber-local model overrides for complex multi-step workflows.
- Automated Optimization: Improve prompt accuracy with MIPROv2 and GEPA optimizers using real data instead of manual prompt tweaking.
- Production Observability: Built-in event tracing, Langfuse integration, and evaluation frameworks for monitoring LLM application performance.
Quick Start
Use the dspy-ruby skill to define a Ruby signature for sentiment analysis and call it with the text "This product is amazing!" to get a structured result with sentiment and confidence score.