rwilinski.ai

Agentic Evals Pyramid

Test Your AI Agent Before It Tests Your Users' Patience

The Principles for Reliable, Safe and Fast AI Agents

Generating structured data with LLMs - Beyond Basics

Benchmarking OpenAI LLMs for JSON Generation

Make Your RAG Suck Less

GraphQL@Edge with global DynamoDB, AWS Lambda and Cloudfront

Lessons learned using Single-table design with DynamoDB