/Orbit Blogs
Notes on AI engineering, system design, and the craft of building software well — from GenAI and agentic systems to the ideas behind shipping things that last.
Read the blog posts or check the About page for more info.
Featured
Letting a Fast Decision Model Drive Mobile QA: Three Practical Examples
Most QA agents wait on an LLM for every tap. TypeSafe's Jev makes quick, structured choices in 70-500ms instead — three examples of the pattern in action.
Shift-Left Security for AI-Assisted Development
AI lets you generate code, tests, and agents from a prompt, but security built for slower, human-written cycles doesn't scale to that speed. Five principles for shifting security left in the AI era.
Stop Giving Users Half-Answers: How to Connect Structured Data with Unstructured Context
Why your AI needs to know both the what and the why — and how to build an agent that connects SQL facts with document context to deliver a complete answer instead of a shrug.
Chunkless RAG: Why Flattening a Document Loses the One Thing That Made It Easy to Read
Chunk-and-embed RAG throws away document structure to make similarity search possible. Here's why reasoning over the original tree — headings, sections, and all — often gets you a better answer.