🤖 AI Summary
Current AI-native software development lacks a systematic architecture to support continuous production, validation, and evolution, hindering long-term reliability and maintainability across diverse scenarios. This work proposes a meta-engineering–enabled architecture that explicitly formalizes product and operational requirements through contract-driven design, employs role-based AI agents to execute tasks, and incorporates adversarial independent verification, four-way failure arbitration, and outer-loop calibration to establish a closed-loop, self-improving system. The architecture uniquely integrates contract compilation, a persistent memory repository, and dual verification mechanisms, enabling AI software to be managed as a continuously operating entity. Early deployment across 17 functional components—exemplified by an in-app payment case—successfully uncovered issues of contract incompleteness and validation boundary limitations, thereby demonstrating the system’s auditability, scalability, and capacity for iterative refinement.
📝 Abstract
AI-native software development is often evaluated at the level of individual models, prompts, or generated artifacts. This framing is insufficient for production environments where software must be continuously produced, verified, deployed, maintained, and adapted across many operational contexts and long time horizons.
We present a meta-engineering harness: a software-production architecture that transforms operational and product feature requirements into explicit contracts, routes work through role-specialized AI agents, performs independent and adversarial verification, and continuously improves itself through structured failure classification and outer-loop calibration.
The harness is designed for settings in which software delivery is not a one-time project but an ongoing operating function. In our motivating application, CTO-as-a-service for small service firms, the system manages websites, booking flows, payment systems, backoffice workflow automations, and AI-agent interfaces as continuously evolving technical infrastructure rather than one-off deliverables.
We describe the layered architecture, including two-pass contract compilation, persistent markdown memory with specialization records, attention-based and independence-based verifications, a four-way failure arbiter, and outer-loop calibration. We report results from an early production deployment spanning 17 features over several weeks, including a detailed in-app payments case study that revealed contract incompleteness and verification-boundary issues. These observations directly drove targeted improvements to the harness.
The contribution is an implemented, measurable, and extensible verification architecture for making AI-native service-as-a-software production reliable, auditable, and improvable over time.