Practical articles about software, technology, and engineering.

OpenStair engineering writing on Flutter, backend systems, documentation, product architecture, open source, and production software delivery.

All articles

Illustration of AI application cost controls across tokens, caching, and model selection
AI

AI Application Costs: Tokens, Caching, and Model Selection

November 25, 2025 · 19 min read

AI Application Costs: Tokens, Caching, and Model Selection explained through practical engineering principles, trade-offs, implementation patterns, and production considerations.

AISoftware EngineeringApplicationsMachine Learning
Illustration of embeddings mapped into a vector database search space
AI

Vector Databases and Embeddings Explained

November 23, 2025 · 18 min read

Vector Databases and Embeddings Explained explained through practical engineering principles, trade-offs, implementation patterns, and production considerations.

AISoftware EngineeringApplicationsMachine Learning
Diagram showing document retrieval, vector search, and an AI model in a RAG system
AI

Retrieval-Augmented Generation: How RAG Systems Work

November 22, 2025 · 19 min read

Retrieval-Augmented Generation: How RAG Systems Work explained through practical engineering principles, trade-offs, implementation patterns, and production considerations.

AISoftware EngineeringApplicationsMachine Learning
Illustration of an AI feature evaluation workflow with model, quality, and monitoring layers
AI

LLM APIs Explained: What Happens Between Prompt and Response

November 21, 2025 · 19 min read

LLM APIs Explained: What Happens Between Prompt and Response explained through practical engineering principles, trade-offs, implementation patterns, and production considerations.

AISoftware EngineeringApplicationsMachine Learning