Intent doesn't flow in one direction. It loops.
Design informs systems, engineering shapes experience, and every artifact feeds back into the next. As AI takes over, strict divisions between roles collapse. The line between implementation and interpretation fades.
The distance between idea and execution disappears, forcing a divergence in how we build.
This is an attempt to surface that shift. How do we build when the loop includes us?
Contents
- Loops, not pipelines
- The collapse of boundaries
- Structural taste
- The second half of AI: the return of the manager
- Comprehensive design
- Conclusion
Loops, not pipelines
Feedback loops have always shaped good software. What’s changing is the speed, depth, and density of those loops—and who’s inside them.
In a loop, there is no "before" and "after." You don’t write the code and wait for the result. You shape the system and feel it respond—immediately, subtly. Every commit is a conversation. Every prompt is a bet.
This changes the ontology of engineering. It’s not about specifying a system and stepping back. It’s about inhabiting the loop long enough to orient it.
The collapse of boundaries
“You become a senior engineer when you stop waiting for specs to be right and start building the conversation instead.”— @graycoding
Design, engineering, and product were never as separate as their org charts suggested. Now, the distinctions are visibly breaking down.
Models blur the interface. Specs become interfaces. Engineers prompt. Designers scaffold.
In this context, the product engineer is a much needed site of convergence. They work across domain models, UX flows, and infrastructure shape—not to “own” a layer, but to ensure intent survives translation.
When boundaries collapse, coordination happens not through handoff, but through coherence.
Structural taste
In this collapsed stack, 2025 saw the rise of "vibe coding"—shaping end-to-end systems in dialogue with the machine, leaning on tacit understanding rather than explicit logic.
But vibe is fragile. Vibe doesn't scale. When it works, it’s grounded in something deeper: structural taste.
“You can’t vibe your way to a good product no matter how good your AI tooling is.” —@thenimmyjeutron
Structural taste is judgment in architecture. It is not a universal standard of high art; it is a specific, local conviction about how things should be.
It’s not about being smarter; it’s about giving a shit when the machine makes it easy not to.
In a world where AI responses are 'good enough,' taste is the act of resistance. It is the refusal to accept the median outcome.
It’s caring about the semantic precision of the domain model. The threshold of a loading spinner. The specific tone of a zero-state. These are the small things that define whether a system is habitable.
The active preservation of coherence against entropy—the rigorous consequence of taste-driven choices—is really the essence of intent.
Vibe carries the energy; taste provides the container.
“Prompting is thinking. The sharper your thoughts, the better the prompts, the better the outputs.” —@rauchg
The second half of AI: the return of the manager
As the friction of implementation dissolves, the role of the engineer expands in two directions simultaneously.
We go deeper. Engineers use AI to tackle complexity that was previously insurmountable. We become comprehensive designers of intricate architectures.
We go wider. If product engineering is the collapse of the stack, this is the compression of execution.
“The second half of AI – starting now – will shift focus from solving problems to defining them. [...] To thrive, we’ll need a timely shift in mindset and skill set, ones perhaps closer to a product manager.” — Shunyu Yao, The Second Half
Here, the end state of the engineer is the manager—but not the manager of people. The cybernetic manager directs the compiler, the agent, and the business logic simultaneously.
In this low-latency loop, the linear relationship dissolves. Implementation informs intent as much as intent causes implementation.
Comprehensive design
Whichever mode we operate in, strict specialization by role is dead. We are all systems thinkers now. What remains is specialization by taste, and a deeper question of responsibility.
This shift creates a new weight. As our leverage scales, so does the impact of our design choices. Every system we shape shapes something larger—economic, ecological, social.
Buckminster Fuller, the original comprehensive designer, framed "Spaceship Earth" as a design challenge: a closed system with limited inputs and global interdependence.
“We are all astronauts on a little spaceship called Earth. But it did not come with an instructions manual.” — Buckminster Fuller
As the loop tightens, the boundary between 'lab' and 'world' becomes porous. What we treat as local variables increasingly triggers global side effects.
The challenge is to build systems that don’t just function, but cohere. Systems that treat life not as an edge case, but as a design constraint.
Spaceship Earth is our shared platform. We’re constantly pushing updates.
Conclusion
Intent initiates; responsibility sustains.
Whether you are deepening the stack or expanding into management, the requirement is the same: to hold the loop open. To interpret, to structure, and to guide.
The product is not the end. It’s another beginning.