Why a New AI Programming Manifesto Is Needed – Lessons from the Agile Revolution
The article argues that after 24 years since the Agile Manifesto, AI-driven programming has created a fresh crisis of role confusion, unpredictability, and security risks, and proposes a new AI Programming Manifesto to guide developers toward responsible, human‑centered, and safe AI‑assisted software engineering.
1. A New Agile Movement After 24 Years
Twenty‑four years after the original Agile Manifesto illuminated software development, AI is now reshaping programming at a paradigm‑shifting pace, prompting a call for a fresh "AI Programming Manifesto" to define new coding principles.
2. Introduction: The Best and Worst of Times
Since late 2022, large‑model breakthroughs such as ChatGPT, GitHub Copilot, Claude Code, Devin, and Cursor have flooded the industry, making the dream of "everyone a developer" feel imminent while also generating anxiety and hype.
Developers experience both the magic of AI‑generated code and the hidden pitfalls that accompany it.
3. Historical Echo: The 24‑Year‑Old "Call to Arms"
In 2001, the heavyweight‑laden waterfall model stifled projects, leading 17 pioneers to draft the Agile Manifesto at Snowbird, Utah, which introduced values that still guide software engineering today.
Kent Beck
Robert C. Martin
Martin Fowler
Jeff Sutherland and Ken Schwaber
The manifesto offered abstract values, not concrete tools, yet it became a lighthouse for the industry.
4. Historical Similarity: We Need a New Breakthrough
Just as the Agile movement addressed a crisis of rigidity, today’s AI programming chaos—role confusion, loss of trust, and rising risks—demands a collective, consensus‑driven effort.
5. Triple Dilemma: Three Typical AI Programming Problems
Problem 1: Human‑Machine Role Confusion – "Who Am I? Who Is the AI?"
AI blurs traditional responsibilities, leading to "blame‑shifting" when AI‑generated code causes production bugs, and turning developers from creators into reviewers.
It also shifts authority from senior engineers to junior developers who can leverage powerful AI tools.
When AI takes the keyboard, where do developers place their hands?Problem 2: Randomness and Hallucination – "Is Code Science or Magic?"
Large language models are probabilistic, producing non‑deterministic outputs and occasional hallucinations that generate nonexistent APIs or subtle logical errors.
These issues force developers to spend multiple times the effort to verify and test AI‑generated code.
We build deterministic worlds with code, yet AI introduces probabilistic fog.Problem 3: Code Quality and Security Risks – "AI: Angel or Trojan Horse?"
AI may suggest outdated libraries, produce hard‑to‑maintain code, or embed hidden vulnerabilities, turning fast delivery into technical debt and exposing systems to security threats.
Feeding proprietary code and data to third‑party AI services also raises privacy concerns.
AI accelerates code delivery while simultaneously accelerating risk.6. Echo from History: From the Agile Manifesto to the AI Programming Manifesto
The same three dilemmas—role confusion, trust loss, and risk escalation—mirror the challenges the Agile pioneers faced, and the solution lies not in new tools but in renewed values and principles.
7. Breakthrough: Crafting an AI Programming Manifesto for Our Era
A diverse group of developers, architects, and AI practitioners formed the AI Programming Community and drafted a manifesto to guide the next generation of software engineering.
GitHub repository:
https://github.com/AI-Programming-Community/AI-Programming-Manifesto8. Manifesto Core Principles
Goal Achievement – Prioritize solving real problems over showcasing AI tricks.
Human‑AI Co‑Creation – Humans set direction; AI assists.
Embrace Change – Leverage AI to transition from traditional to intelligent programming.
Clear Insight – Understand AI capabilities and limits rationally.
Process Control – Keep AI‑assisted development predictable.
Continuous Safety – Maintain code quality and system maintainability.
These six keys address the three dilemmas by redefining roles, ensuring determinism, and safeguarding quality.
9. Birth of the Manifesto: Community Leadership
The manifesto was spearheaded by "Joe Bangzhu" (Joe Liang), a veteran of the Chinese Agile community, who translated major works and advocated DevOps and continuous delivery.
Supported by a team of contributors, the community invites developers to read, discuss, and co‑create the manifesto on GitHub.
10. Vision and Invitation
The AI Programming Community seeks to rebuild software engineering order, turning developers from AI reviewers into empowered creators, and invites anyone to join, star the repository, raise issues, or submit pull requests.
Together we can end the "AI software crisis" and usher in a mature, trustworthy era of intelligent software engineering.
Continuous Delivery 2.0
Tech and case studies on organizational management, team management, and engineering efficiency
How this landed with the community
Was this worth your time?
0 Comments
Thoughtful readers leave field notes, pushback, and hard-won operational detail here.
