The answer, my friendow, is blowing in the context window [1]…
_______
…LLMs already "know" these books deeply, but without a structured prompt scaffold they apply that knowledge inconsistently and at low confidence. Giving the model a explicit lens — "review this as if you're checking against Clean Code heuristics C1–C36" — concentrates attention and dramatically reduces hallucinated or off-topic feedback…
…
Where I'd push back or warn you:
Context collapse is your #1 enemy. Clean Code was written for Java in 2008. DDIA is about distributed systems at scale. If you apply the Clean Code reviewer to a 50-line Python script, you'll get pedantic nonsense about function length when the actual problem might be that the data model is wrong. Your skill selection logic needs to be domain-aware, not just "throw all skills at every file"…
> …perspectives from people
> who are better at reading
> if studies are quality or not…
I'm by no means an expert at telling what the quality of a given research paper is.
But, without even reading the whole PDF [1] of this particular paper, it's super easy to tell that the authors are all from pro-vibe coding consultancies [2][3][4]
Y Combinator founders, and proper startup founders in general are not outsiders. They aren't, and never been, Upwork customers, and in fact every sane VC will reject a startup that uses any sort of outsourcing to build their offering, because they know that not just it doesn't work, can't possibly work, but the very idea of trying it shows that you don't know what you are doing and are thus uninvestable.
So i don't mean people like YC founders (i wouldn't even talk to one if i met them - surely there won't be money to make there). These are mostly, people from different spheres completely who just walked into money for some irrelevant reason and decided to start something online, out of random. For almost all of my clients, mine was their first, and last, software project ever.
I asked the question because I wondered if or how AI-assistance might be used more these days. By either the freelancers in their delivering their services, or by buyers who might be figuring they don't need to hire a freelancer for whatever reason these days.
While I do pay for an OpenAI (ChatGPT) account, I wouldn't ever pay someone to use it for me, so I don't know. Given how it works, I would be only results driven, and if the results I want come easily through AI, I would have already done it that way.
I don't speak for everyone, but I have a hard time imagining someone paying for someone else to .... prompt for things on their behalf. Especially since the prompt I would have to provide you is likely to be sufficient for the AI directly.
I suppose I could have made it clearer that the reply would explicitly make readers aware that the analysis was done by a Robo — i.e., an LLM.