# The Productivity-Reliability Paradox: Specification-Driven Governance for AI-Augmented Software Development

arXiv: https://arxiv.org/abs/2605.01160 · HTML: https://mlsanity.com/paper/2605.01160/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 65 references that are in the map.
- First posted on arXiv 1 May 2026.

## Builds on (most cited first, 21 of 21)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [The Impact of AI on Developer Productivity: Evidence from GitHub Copilot](https://mlsanity.com/paper/2302.06590/) (2023)
- [Grounded Copilot: How Programmers Interact with Code-Generating Models](https://mlsanity.com/paper/2206.15000/) (2022)
- [GitHub Copilot AI pair programmer: Asset or Liability?](https://mlsanity.com/paper/2206.15331/) (2022)
- [Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivity](https://mlsanity.com/paper/2507.09089/) (2025)
- [How much does AI impact development speed? An enterprise-based randomized controlled trial](https://mlsanity.com/paper/2410.12944/) (2024)
- [From Copilot to Pilot: Towards AI Supported Software Development](https://mlsanity.com/paper/2303.04142/) (2023)
- [Spec-Driven Development:From Code to Contract in the Age of AI Coding Assistants](https://mlsanity.com/paper/2602.00180/) (2026)
- [Inference economics of language models](https://mlsanity.com/paper/2506.04645/) (2025)
- [Comprehensive Evaluation and Insights into the Use of Large Language Models in the Automation of Behavior-Driven Development Acceptance Test Formulation](https://mlsanity.com/paper/2403.14965/) (2024)
- [Test-Driven AI Agent Definition (TDAD): Compiling Tool-Using Agents from Behavioral Specifications](https://mlsanity.com/paper/2603.08806/) (2026)
- [Evaluating LLM-Based 0-to-1 Software Generation in End-to-End CLI Tool Scenarios](https://mlsanity.com/paper/2604.06742/) (2026)
- [The Impact of LLM-Assistants on Software Developer Productivity: A Systematic Review and Mapping Study](https://mlsanity.com/paper/2507.03156/) (2025)
- [Bias in the Loop: How Humans Evaluate AI-Generated Suggestions](https://mlsanity.com/paper/2509.08514/) (2025)
- [Scaling Test-Driven Code Generation from Functions to Classes: An Empirical Study](https://mlsanity.com/paper/2602.03557/) (2026)
- [Complement or substitute? How AI increases the demand for human skills](https://mlsanity.com/paper/2412.19754/) (2024)
- [Cognitive Biases in LLM-Assisted Software Development](https://mlsanity.com/paper/2601.08045/) (2026)
- [Human-AI Synergy in Agentic Code Review](https://mlsanity.com/paper/2603.15911/) (2026)
- [VibeContract: The Missing Quality Assurance Piece in Vibe Coding](https://mlsanity.com/paper/2603.15691/) (2026)
- [Tiered Super-Moore's Law: Price Evolution, Production Frontiers, and Market Competition in Large Language Model Inference Services](https://mlsanity.com/paper/2603.28576/) (2026)
- [Behaviour Driven Development Scenario Generation with Large Language Models](https://mlsanity.com/paper/2603.04729/) (2026)

## Built on by (most cited first, 3 of 3)

- [Governed AI-Assisted Engineering: Graduated Human Oversight for Agentic Code Generation in Regulated Domains](https://mlsanity.com/paper/2606.22484/) (2026)
- [How Do AI Coding Agents Contribute to Software Development? an Empirical Study of Agentic Pull Requests](https://mlsanity.com/paper/2607.21832/) (2026)
- [Specification-first convergence with an AI coding agent: a case study of dismantling a core architectural invariant across 189 files in a 717k-line codebase with no test oracle and no human code review](https://mlsanity.com/paper/2608.12440/) (2026)

## Abstract (arXiv)

Since 2022, AI-powered coding assistants have produced contradictory evidence: controlled studies report 20-56% productivity gains on well-scoped tasks, while the most rigorous RCT documents a 19% slowdown for experienced developers, and telemetry across 10,000+ developers shows 98% more pull requests but 91% longer review times with flat delivery metrics. This paper argues these findings constitute the Productivity-Reliability Paradox (PRP): a systematic phenomenon emerging from non-deterministic code generators and insufficient specification discipline. Through a multivocal literature review of 67 sources (2022-2026), this paper: (1) formally defines the PRP with three moderating variables (task abstraction, codebase maturity, developer experience) and two amplifying mechanisms (code review bottleneck, context window constraint); (2) proposes the AI-Augmented Methodology Taxonomy (AAMT), classifying six methodologies under three AI integration tiers; (3) introduces the Specification Governance Model (SGM), grounded in Transaction Cost Economics, with a practical governance decision guide; and (4) evaluates Spec Kit and TDAD as SGM instantiations via a four-month pilot study. Specification discipline, not model capability, is the binding constraint on AI-assisted software dependability.