Agile V: AI 증강 엔지니어링을 위한 개방형 표준

Agile V™ is a significant shift from "Agile vs. V-Model" to a unified approach. Classical Scrum, while effective for human-scale product development, optimizes for adaptability through time-boxed ceremonies and team-level feedback loops. However, in the AI era where continuous change, autonomous execution, and system-level assurance are required, it lacks intrinsic mechanisms for verifiable, auditable quality at scale. The traditional V-Model provides rigor and traceability but remains rigid and project-bound. Agile V™ unifies both into an Autonomous Quality Management System (AQMS), continuous, verifiable, auditable, and human-led. Whether you ship software, firmware, or hardware in regulated or safety-critical domains, the same structure applies. This approach has been validated on complex hardware/software projects, the proof of life that backs the manifesto. Agile V™ is published as an open standard under CC BY-SA 4.0. The Agile V™ Workflow: The Infinity Loop In this model, the "V" isn't a one-time journey; it's a high-frequency vibration. The platform enforces the V structure at the task level, not just the project level. 1. The Left Side: Intent & Decomposition Input: Human provides high-level "Product Intent". Requirement Agent: Generates PRDs and Traceable User Stories. The Guardrail: A Logic Agent checks requirements for ambiguity or hardware constraints (e.g., "Are these GPIO pins actually available on the chosen MCU?"). Human Gate 1: User approves the "Blueprint". 2. The Apex: Synthesis Build Agent: Generates the artifacts (Code, PCB Schematics, HDL or Firmware). Parallel Action: The Test Design Agent reads the Requirements (not the code!) to build the verification suite. This prevents "success bias", where tests only check what the code happens to do. 3. The Right Side: Verification & Compliance Verification Agent: Executes tests against the Build artifacts. Audit Agent: Records the "Chain of Thought": why a specific component was chosen and how it was tested. This generates ISO/GxP-ready logs automatically. Human Gate 2: User reviews the Validation Summary (the "Evidence"). The Agile V™ Manifesto We are practitioners who build software, firmware, and hardware with AI-assisted tools, and we need a shared standard for doing it safely and auditably. We are uncovering better ways of developing complex systems by doing it and helping others do it. Through this work we have come to value: These values guide how we use AI agents: we prefer the left over the right. Verified Iteration over Unchecked Velocity Speed is a byproduct of confidence; verify every step before moving to the next. Traceable Agency over Opaque Autonomy Maintain a clear audit trail of who, human or agent, made which decision. Living Compliance over Static Documentation Compliance must be an inherent outcome of the workflow, not a post-hoc chore. Human Curation over Human Execution Humans lead intent, design, and review. Execution is assisted or automated. That is, while there is value in the items on the right, we value the items on the left more. The 12 Principles of Agile V™ Continuous Validation: Testing is not a phase; it is the shadow of development. The Single Source of Truth: Requirements, code, and tests are mathematically linked so AI agents can keep them consistent. Human-in-the-Loop (HITL): Humans shift from "Doers" to "Designers and Auditors." Hardware-Aware Software: AI agents must validate physical constraints (PCB/Firmware) as early as code logic. Regulatory Readiness: Compliance is a byproduct of the workflow, not a frantic effort at the end. Decompositional Clarity: No artifact is built until the AI and Human agree on its "Definition of Done". The "Red Team" Protocol: Every build agent is challenged by an independent verification agent. Minimalist Meetings: Refinements are replaced by asynchronous Agent-to-Human reviews. Decision Logging: Every "Why" is captured in real-time for ISO and GxP integrity. Sustainable Rigor: The system prevents shortcuts that lead to technical or regulatory debt. Cross-Domain Synthesis: Bridging the gap between electrical, mechanical, and software agents so that system-level behavior is consistent. Simplicity: The art of maximizing the amount of "busy work" not done, so humans focus on design and judgment, not repetitive tasks. Agile V™ Skills To help you adopt the framework in practice, we maintain a curated set of pre-defined AI agent skills. These skills, available for Cursor or other compatible tools, encode Agile V™ principles directly into your development workflow. They guide requirements decomposition, enforce traceability between intent and implementation, and structure verification and compliance steps. Start by applying one Agile V™ principle in your next iteration, and let us know how it goes — your feedback will help shape the evolving open standard.