Engineering blog

Notes from the AI engineering trenches.

Architecture, performance, costs, and the occasional hard lesson. We write when we have something concrete to share — no SEO bait, no content marketing fluff.

LLM EngineeringAugust 20, 2026 7 min read

Why every production LLM app needs a two-stage intent router

A monolithic LLM that handles everything — classification, planning, tool use — is slow, expensive, and hard to debug. A two-stage architecture with a small classifier upstream fixes all three.

#llm#architecture#rust#ollama

InfrastructureAugust 5, 2026 9 min read

We replaced Pinecone with Qdrant + SQLite. Here is the playbook.

For most production AI applications, self-hosting your vector store is 10x cheaper and faster than a managed service. Here is how we did it for AetherFS.

#vector-search#qdrant#self-hosted#cost-optimization

ProductJuly 18, 2026 8 min read

Designing an LLM UX for users who cannot see the screen

Building conversational AI for blind users forced us to rethink every UX assumption we had. Here are the four biggest lessons that apply to any LLM product.

#accessibility#ux#llm#product-design