No BS AI development: practical Ruby tutorials that actually work.
Building a research agent with CodeAct where the LLM generates Ruby code on the fly
Vicente Reig
Fractional Engineering Lead
Learn lightweight context engineering in Ruby. We'll incrementally build a chat agent with ephemeral memory and cost-based routing—starting from the simplest possible loop and layering complexity only when needed.
Vicente Reig
Fractional Engineering Lead
A quick walkthrough of how to turn LLM calls into composable building blocks in Ruby. With evaluator loops, you get cheap iterations, clear critiques, and real observability into each step. Great for shipping better sales pitches without guessing what the model is doing (or overspending on tokens).
Vicente Reig
Fractional Engineering Lead
Route every ticket to the right Language Model, only escalate to heavy LLMs when needed, keep every hop observable, and never touch a handwritten prompt along the way.
Vicente Reig
Fractional Engineering Lead
Token-Oriented Object Notation keeps your nested Sorbet structs intact—something flat CSV rows simply can’t do when you prompt large language models.
Vicente Reig Rincon de Arellano
Fractional Engineering Lead
DSPy.rb now pairs BAML schemas with Sorbet::Toon payloads. The combo keeps Enhanced Prompting simple while saving ~9000 schema tokens and ~2400 data tokens per request.
Vicente Reig Rincon de Arellano
Fractional Engineering Lead
When signatures hit 5+ fields, JSON Schema overhead eats hundreds of tokens per call. BAML keeps them compact—no retraining needed.
Vicente Reig Rincon de Arellano
Fractional Engineering Lead
Head-to-head comparison of enhanced prompting vs native structured outputs across OpenAI, Anthropic, and Google models
Vicente Reig
Fractional Engineering Lead
How to use LLM judges to evaluate AI SDR campaigns with human-like reasoning, going beyond rule-based metrics to assess prospect relevance, personalization, and professional tone.
Vicente Reig
Fractional Engineering Lead
An architecture designed for high throughput on a fiber-based concurrent execution model, event-driven telemetry system, and production-ready architecture delivering real performance improvements with minimal overhead.
Vicente Reig
Fractional Engineering Lead
See how DSPy.rb's executor-driven telemetry keeps real-time visibility without slowing down your LLM workflows
Vicente Reig
Fractional Engineering Lead
DSPy.rb now provides true async concurrency for LLM retries and operations, eliminating blocking delays while maintaining reliability
Vicente Reig
Fractional Engineering Lead
How DSPy.rb's async architecture enables efficient background processing with Sidekiq, avoiding thread blocking during LLM API calls
Vicente Reig
Fractional Engineering Lead
DSPy.rb v0.20.0 introduces comprehensive program serialization and storage capabilities, allowing you to save, load, and share optimized DSPy programs with full state preservation.
Vicente Reig
Fractional Engineering Lead
DSPy.rb v0.20.0 introduces full Google Gemini support, bringing Google's state-of-the-art multimodal AI capabilities to Ruby developers with complete type safety and structured outputs.
Vicente Reig
Fractional Engineering Lead
DSPy.rb v0.20.0 introduces DSPy.with_lm for elegant temporary language model overrides using Ruby's fiber-local storage, enabling clean concurrent patterns and better model management.
Vicente Reig
Fractional Engineering Lead
Major release brings Google Gemini support, fiber-local contexts, and program serialization to DSPy.rb
Vicente Reig
Fractional Engineering Lead
DSPy.rb now supports Ollama, bringing type-safe structured outputs to local LLM development. Learn how to build cost-effective AI applications with zero API charges during development.
Vicente Reig
Fractional Engineering Lead
A technical deep-dive into DSPy.rb's multi-strategy JSON extraction system, showing exactly how it handles OpenAI, Anthropic, and other providers
Vicente Reig
Fractional Engineering Lead
Learn how to use DSPy.rb's raw_chat API for benchmarking monolithic prompts and migrating to modular implementations
Vicente Reig
Fractional Engineering Lead
How DSPy.rb's single-field union types with automatic type detection simplify AI agent development
Vicente Reig
Fractional Engineering Lead
Discover how DSPy.rb's type-safe prediction objects catch integration errors before they reach production, giving you the confidence to ship AI features faster.
Vicente Reig
Fractional Engineering Lead
Deep dive into Program of Thought (PoT) - a powerful approach that separates reasoning from computation. Compare it with CodeAct and ChainOfThought to find the right tool for your AI applications.
Vicente Reig
Fractional Engineering Lead
How DSPy.rb's new reliability features make JSON extraction from LLMs actually reliable
Vicente Reig
Fractional Engineering Lead
CodeAct now ships as a standalone gem with dedicated README docs.
Vicente Reig
Fractional Engineering Lead
Step-by-step guide to creating tool-using AI agents with DSPy.rb. Learn how to build agents that can reason about their actions and solve complex multi-step problems.
Vicente Reig
Fractional Engineering Lead
How DSPy.rb embraces Ruby conventions to make AI development feel natural. Learn about the design decisions that make DSPy.rb uniquely Ruby.
Vicente Reig
Fractional Engineering Lead
Learn how to systematically evaluate LLM applications using DSPy.rb's evaluation framework, from basic metrics to advanced quality assessment.
Vicente Reig
Fractional Engineering Lead
Learn how to systematically test and measure your LLM applications using DSPy.rb's evaluation framework
Vicente Reig
Fractional Engineering Lead
See how DSPy.rb achieves 3x performance improvements using Ruby's excellent async capabilities. Real measurements from a practical coffee shop agent example.
Vicente Reig
Fractional Engineering Lead