AI can assist architects by generating multiple perspectives and surfacing trade-offs rather than producing a single answer. Virtual think tanks composed of LLM participants can present technical, organizational, ethical, and other viewpoints to broaden option awareness. Properly configured virtual think tanks encourage critical evaluation, force explicit decision-making, and preserve human accountability. Writing prompts for virtual think tanks is itself a creative act that reframes problems and provokes new ideas. Integrated AI tools in development workflows change how code and design choices are discovered, replacing some prior resources while amplifying the need for deliberate analysis.
Author's note: This article is based on extensive interaction with LLMs. Reading the LLM outputs can be quite tedious. When I feel it contributes significantly, the outputs of the LLM are included in an appendix. Otherwise the article includes only brief quotes. In any case, the reader is encouraged to try out the prompts on your LLM of choice. You might discover something surprising.
Rather than provide an answer, AI can be used to consider trade-offs. The virtual think tank is a powerful tool in considering trade-offs. Done properly, virtual think tanks will provide us with ideas and perspectives that we might not have thought of otherwise. Architecture has many aspects-Technical, organizational, ethical, and more. A virtual think tank will allow us to "have a discussion" that takes all considerations into account.
Collection
[
|
...
]