Nidus: Externalized Reasoning for AI-Assisted Engineering

TL;DR

Nidus is a governance system that externalizes engineering methodologies for AI-assisted software delivery, ensuring compliance and verification through external constraints and formal development history.

Contribution

It introduces recursive self-governance, stigmergic coordination, proximal spec reinforcement, and governance theater prevention for reliable AI-assisted engineering.

Findings

Successfully managed a 100,000-line system with multiple LLMs under proof obligations.

Externalized constraints enforce engineering invariants reliably.

The system's development history guarantees compliance and monotonic growth.

Abstract

We present Nidus, a governance runtime that mechanizes the V-model for AI-assisted software delivery. In the self-hosting deployment, three LLM families (Claude, Gemini, Codex) delivered a 100,000-line system under proof obligations verified against the current obligation set on every commit. The system governed its own construction. Engineering invariants - traced requirements, justified architecture, evidenced deliveries - cannot be reliably maintained as learned behavior; assurance requires enforcement by a mechanism external to the proposer. Nidus externalizes the engineering methodology into a decidable artifact verified on every mutation before persistence. Organizational standards compile into guidebooks - constraint libraries imported by governed projects and enforced by decidable evaluation. Four contributions: (1) recursive self-governance - the constraint surface constrains mutations to itself; (2) stigmergic coordination - friction from the surface routes agents without central control; (3) proximal spec reinforcement - the living artifact externalizes the engineering context that RL and long-chain reasoning try to internalize; the specification is the reward function, UNSAT verdicts shape behavior at inference time, no weight updates; (4) governance theater prevention - compliance evidence cannot be fabricated within the modeled mutation path. The constraint surface compounds: each obligation permanently eliminates a class of unengineered output. The artifact's development history is a formal development - every state satisfies all active obligations, and the obligation set grows monotonically.