10 Where the method costs and where it falls short

10 · Where the method costs and where it falls short

The method has limits, and some have already emerged in use.

Limit	Implication
Initial overhead	Writing and maintaining the specification has a cost that is not justified for short or throwaway tasks. The method pays off on work of duration and complexity, not on the single request.
Context saturation	The additive character makes the specification grow, and a wide specification held entirely in context saturates the model's attention. Distillation and partitioning (chapter 7) mitigate the problem but do not eliminate it; it is the method's most tangible limit, and it strains above all models with a narrow context window.
Risk of over-structuring	The discipline can degenerate into apparatus: decisions where an obviousness would suffice, structure where prose is needed. It is the reverse of the tendency to overdo treated in chapter 3; the corrective — declared scope and the good-enough criterion — reduces the risk but does not eliminate it, and requires the judgement of a competent operator.
Personalities not sufficient	As stated, distinct interlocutors do not guarantee distinct reasoning. The benefit depends on the design of the roles, not on their mere presence.
Dependence on human judgement	The decision remains a human act. The method improves the information on which the decision is founded; it does not replace it, nor does it make up for the lack of a criterion.
Evidence from a single domain	The experience that supports the method comes from software development, where intent is formalisable in advance and error surfaces early. That it pays off in the same way where a rapid test of correctness is missing, or where intent and product co-evolve, is a reasonable expectation, not a demonstrated fact. It must be verified domain by domain.

When not to use it

The method pays off when the cost of losing the reasoning exceeds the cost of fixing it. Below that threshold it is ballast. In concrete terms, one does not adopt it for tasks that are over in an hour, for throwaway prototypes, for reversible, low-cost decisions, for early explorations in which fixing choices too soon would narrow the field, and when an external criterion for verifying whether the work is correct is missing — because there the specification orders the reasoning without being able to ascertain its validity. The same caution holds for multiple interlocutors: they are added only if they produce real divergences, not by reflex.

There is, finally, what this document does not claim. It does not maintain that the method produces better results in any measurable sense on an arbitrary task: it maintains that it makes the work traceable, recoverable and open to more perspectives, and that these are process advantages, distinct from the quality of the single output. Generalisation beyond the experience it is drawn from must be verified case by case.

---

← 09 · Why the method holds · The Method · 11 · From method to tool →