The AI Design Authority
We are at an inflection point in software development. The discussion often revolves around which AI writing the best code (Claude vs. ChatGPT) or where where that AI should live (IDE or CLI). But that is not the right question.
The problem is not the generation of code. It is the validation of it.
If we embrace AI as “Vibe Coders” — where we specify intent and AI handles execution — we create a huge surge of new software. A swarm of AI agents can generate in one minute more code than a senior developer can review in a week. The human has become the bottleneck.
The solution is not more more people. The solution is an AI Design Authority.
From Craftsman to Factory Director
Traditionally the "Design Authority" is a small group of architects who meet weekly or monthly to approve or reject a design. In a world of high-velocity AI development that model is hopelessly outdated. It is too slow and too reactive.
If we switch to "Disposable Code" — software we don't endlessly refactor but discard and regenerate when requirements change — our role changes fundamentally. We are no longer bricklayers laying stone by stone. We are the architects of the factory that prints the walls.
But who checks that those walls are straight?
The "Gauntlet": An automated trial by fire
An AI Design Authority is not a person, but a pipeline. A "Gauntlet" that every line of generated code must fight through to reach production. This process does not replace human code review with nothing, but with something better.
It operates in three layers:
1. The Executive Power (The Generation)
We don't ask one AI for a solution, we ask three. We have Gemini 3, GPT-5 and an open-source model (such as Llama) work in parallel on the same problem. This prevents tunnel vision and breaks the "laziness" that LLMs sometimes suffer from. This approach is also scientifically researched and demonstrates that you can prevent AI hallucination and build very long chains without errors
2. The Hard Filter (The Law)
There is no room for debate here. Code must compile. Linters must not complain. And crucially: the Black Box Tests must pass. We do not test whether the function works internally (that can be manipulated by the AI); we test whether the system behaves as required from the outside. Fails the test? Straight to the trash.
3. The Soft Filter (The AI Jury)
This is the real innovation. The remaining solutions are submitted to a specialized “Voting AI”. This agent does not write code, but reads code. It is trained on our architectural principles, security requirements (OWASP, ISO) and compliance rules (EU AI Act).
It votes: “Solution A is faster, but Solution B is safer and aligns better with our microservices architecture.”
The winner goes into production.
The Separation of Powers of Software
This model enforces a separation of powers that is missing in many teams.
- The Legislative Power (The Architect): The Architect writes the "Constitution." The prompts, the architecture documents (
project-description.md, rules.md, skills.md en principles.md), the hard requirements. The architect determines what what we build, who builds it, how and why. - The Executive Branch (The Coding Agents): They execute. Fast, cheap and under the auspices of human developers.
- The Judicial Branch (The Design Authority): An independent AI layer that ensures compliance with the law.
Conclusion: The Architect's new role
It frees us from the tyranny of syntax errors and lets us focus on what we are good at: systems thinking. Fact-finding. Structure and decision-making.
The question is not whether AI can write our code. That matter is already settled. Code will largely become a disposable product.
The question is: Do you dare let go of control over the code to thereby gain control over the quality to recover?
let me know
