Editorial / AI Engineering

The demo-to-production gap is a system boundary problem

Most AI projects stall between a convincing demo and a dependable system. The cause is rarely the model — it is unclear boundaries around data, authority, failure, and ownership.

Jul 15, 20262 min read

Aug 20, 2026Go

One API for CRM and ERP: structuring a Go operations backend

When customers, orders, inventory, and invoicing drift apart across tools, the fix is a system boundary, not another integration. How we structured our Go operations backend.

2 min read

Aug 5, 2026LLM

Grounded answers need more than retrieval: what we learned building Pixi-EQ

Query planning, multi-step retrieval, and answer verification are what turn a RAG prototype into a system whose answers you can check. Notes from building Pixi-EQ.

2 min read