Home · Getting Started · Model · Assessment Hub · Roadmap
References and Acknowledgements
References
This framework synthesizes insights from research literature, industry reports, engineering practice, and publicly documented case studies.
The sources below provide empirical grounding and conceptual background for the model.
Foundational Perspectives on AI-Native Software Development
These works explore the trajectory from assistive AI tools toward autonomous software production systems.
- Shapiro, D. — The Five Levels: from Spicy Autocomplete to the Dark Factory, Jan. 2026.
- StrongDM — The StrongDM Software Factory: Building Software with AI, Feb. 2026.
- StrongDM — Attractor (GitHub repository), 2026.
- Willison, S. — How StrongDM Builds Software Without Looking at the Code, Feb. 2026.
Specification-Driven and Intent-Based Development
These sources describe emerging practices where structured intent, specifications, or scenarios drive implementation.
- Delimarsky, D. — Spec-driven development with AI: Get started with a new open source toolkit, GitHub Blog, Sep. 2025.
- GitHub — spec-kit (repository), 2026.
- GitHub — Specification-Driven Development, spec-kit documentation, 2026.
- Böckeler, B. — Spec-Driven Development Tools and Practice, Thoughtworks Insights, Oct. 2025.
Agentic Software Development and Autonomous Systems
These works document real-world agent workflows, background coding systems, and agent orchestration patterns.
- Microsoft — An AI-led SDLC: Building an End-to-End Agentic Software Development Lifecycle, Feb. 2026.
- Levret, A. — Evaluating Agentic AI Systems: Agentic Metrics, Microsoft Foundry Blog, Apr. 2025.
- Gaidar, T., Copty, F. — Agentic AI Research Methodology — Part 2, Microsoft Foundry Blog, Sep. 2025.
- Morris, K. — Humans and Agents in Software Engineering Loops, Thoughtworks Insights, Mar. 2026.
- Böckeler, B. — Harness Engineering, Thoughtworks Insights, Feb. 2026.
Industry Case Studies of Agent Adoption
These sources describe concrete implementations of AI agents in large engineering organizations.
- Charas, M., Bruggmann, M. — Spotify’s Background Coding Agent (Honk) — Part 1, Spotify Engineering, Nov. 2025.
- Charas, M., Bruggmann, M. — Context Engineering for Background Coding Agents, Spotify Engineering, Nov. 2025.
- Charas, M., Bruggmann, M. — Feedback Loops for Predictable Agent Results, Spotify Engineering, Dec. 2025.
- Prakash, A., Payyavuala, N. — Contextual Agent Playbooks and Tools at LinkedIn, LinkedIn Engineering Blog, Jan. 2026.
- Anthropic — How Anthropic Teams Use Claude Code, Jul. 2025.
AI Impact on Software Engineering Productivity
These works examine measurable effects of AI tools on development output and workflow.
- Anthropic — Economic Index: AI’s Impact on Software Development, Apr. 2025.
- Becker, J., et al. — Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivity, METR, Jul. 2025.
Organizational and Enterprise Adoption
These sources focus on large-scale transformation challenges and maturity assessment approaches.
- Grid Dynamics — AI SDLC Maturity Assessment for Enterprise Engineering Teams, 2026.
Broader Context: AI Adoption and Engineering Practice
These widely cited reports and studies provide additional empirical background.
- Stanford Human-Centered AI — AI Index Report
- McKinsey & Company — The State of AI reports
- Boston Consulting Group — AI at Scale reports
- MIT Sloan Management Review — AI strategy research
- Google — DORA State of DevOps reports
- GitHub — State of the Octoverse
Governance and Risk Frameworks
Relevant standards and guidance influencing responsible AI deployment.
- NIST — AI Risk Management Framework
- ISO/IEC standards related to software engineering and AI governance
- OECD AI Principles
This framework does not claim endorsement by any organization listed above.
All interpretations and syntheses are the responsibility of the author(s).
Acknowledgements
This framework benefited from discussions with engineering leaders, researchers, and practitioners across industry and academia.
Feedback from early readers and reviewers helped clarify concepts and improve the structure of the model.
The author(s) also acknowledge the broader open-source and research communities whose work on software engineering, AI systems, and organizational transformation informed this synthesis.
Any errors, interpretations, or omissions remain the responsibility of the author(s).
This project is independent and does not represent the views of any employer or organization that the author(s)/ contributors are associated with in the present or the past.
↑ Back to top · Home