Why We Still Don't Trust AI-Generated Code: The Archright Trinity
Source: Dev.to
⚠️ Collection Error: Content refinement error: Error: 429 429 Too Many Requests: you (bkperio) have reached your weekly usage limit, upgrade for higher limits: https://ollama.com/upgrade
“You just can’t trust code written by AI.” Until right before I decided to resign, this was the sentence I heard most often in real engineering teams. I stood in the middle of that contradiction, in agony, drilling into the root cause. No. Organizations forced engineers to review hundreds of lines produced in seconds through naked-eye inspection and overtime. When intent is not preserved, teams cannot prove whether generated code matches architectural decisions. Without deterministic controls, generated code remains a probability game. Many AI outputs are operationally acceptable in the moment but logically under-proven. Archright exists to solve this asymmetry as a system. It freezes builder intent and context as durable records, like a GitHub commit log for reasoning. This system is not a simple log. Requirements input In short, code is only one output that must satisfy this intent. Why Nim instead of Rust? Language choice is not a matter of taste. Intent (high level) → Constraints (intermediate form) → Code (low level) We chose a language that minimizes the cost of maintaining this connection. We chose a language that allows this question to be handled before compile-time output. Trying to block probabilistic failure with another probabilistic tool is mathematically hollow. Most security incidents emerge precisely from that neglected 0.01% gap. This verification is not a post-hoc review. Convert intent into verifiable rules Validate those rules hold across all states Search automatically for counterexamples that break the rules Stop code generation when a counterexample is found Generate code only when all constraints hold For example: If a request is sent with another user’s ID: In short, we do not “catch bugs.” On top of these three pillars, engineers are no longer janitors cleaning up AI-generated trash. AI writes code. That is exactly the new software-engineering standard Archright proposes, and the reason I began this journey.