AI Isn't Something to Trust — It's Something to Design (Series Final)
Series Final. The four mechanisms covered across this series — knowledge graph, Auto Review, Self-Healing, Recurrence Prevention — plus the non-engineer-PR application that sits on top of them, all hang off a single conviction: AI isn't something to trust; it's something to design. The 'I don't trust AI to fill in the blanks for me' framing this lives inside isn't doubt about generation quality, but the clear-eyed acceptance that AI has no idea what context wasn't handed to it, and that 'ideal behavior with no spec given' is a fantasy. The starting point goes back to 2025, when I was trying to figure out how to make AI actually understand a large codebase — and ran into walls on both context window scaling (lost in the middle, attention dilution) and learning-based approaches (machine unlearning, destructive interference). GraphRAG + MCP became the way out: hand AI only the facts it needs, when it needs them, so it doesn't have to infer. From code-graph (which I burned two months on and threw away) to the current product-graph (cpg). This piece is the philosophy and the trial-and-error behind the whole series: harnesses confine where hallucinations are allowed to happen, design is translating principles into your own use cases, and Coverage 90% as a solo target breaks the implementation.
Disclaimer: "cortex" in this article is the internal codename for an AI platform built in-house at airCloset. It is unrelated to existing commercial services like Snowflake Cortex or Palo Alto Networks Cortex.
Across the five posts of this series I've worked through how cortex's harness is put together, one piece at a time: the overall picture, the knowledge graph, Auto Review, Self-Healing + Recurrence Prevention, and non-engineer PRs. Having walked through all of them, I want to step one level down for the wrap-up. Why am I building this thing in the first place? That's what this post is about.
The five posts might look independent, but the root is one thing, and the series doesn't close cleanly without that one thing being put into words. Together with the philosophy, I want to look back at the failures that don't show up when you only write about what worked — what I threw away, where I tripped — as a reference point for anyone trying something similar.
