Agentic Agile-V: From Vibe Coding to Verified Engineering in Software and Hardware Development

TL;DR

This paper introduces Agentic Agile-V, a process framework that enhances agentic AI coding systems with structured engineering workflows, emphasizing process control and verification over simple automation.

Contribution

It proposes a comprehensive lifecycle model and a taxonomy for agentic engineering artifacts, improving reliability and discipline in AI-assisted software and hardware development.

Findings

Agentic AI improves productivity in some tasks but faces challenges in setup and verification.

The framework separates dialogue from implementation to enhance control and traceability.

Agentic AI increases the importance of requirements, constraints, and verification in engineering.

Abstract

Agentic AI coding systems can inspect repositories, plan implementation steps, edit files, call tools, run tests, and submit pull requests. These capabilities make software and hardware development faster in some settings, but current evidence does not support the simple claim that autonomous code generation automatically improves engineering outcomes. Controlled studies report productivity gains in some enterprise tasks, slowdowns in mature open-source work, moderate but heterogeneous meta-analytic effects, and persistent failures in repository setup, dependency handling, permission gating, and hardware verification. This paper argues that the central problem is no longer prompt engineering; it is engineering process control. It synthesizes evidence from agentic software engineering, GitHub-scale adoption studies, repository-level agent configuration, productivity trials, issue-resolution benchmarks, and hardware/RTL verification research. It proposes Agentic Agile-V, a process framework that uses Agile-V as the lifecycle backbone and a task-level SCOPE-V loop - Specify, Constrain, Orchestrate, Prove, Evolve, and Verify - to convert conversational intent into structured engineering artifacts and acceptance evidence. The paper contributes: (i) a taxonomy of minimum input artifacts for agentic software, firmware, and hardware work; (ii) a conversation-to-contract gate that separates exploratory dialogue from implementation; (iii) risk-adaptive feature, bug-fix, testing, and hardware workflows; and (iv) an evidence-bundle acceptance model for agent-generated artifacts. The paper concludes that agentic AI does not eliminate engineering discipline; it increases the value of requirements, constraints, traceability, independent verification, and human approval.