[laszlojamf]

The caveat here is, as TFA states, is that you need to have "every constraint on the table". And that is almost never the case. Unless you create something in a mature domain, where everything has already been explored, you _won't know_ what the constraints are.

You can spend three months in whiteboard sessions planning out the perfect solution, and then your plan falls apart the second you start implementing, because the real world imposes constraints on you that were practically impossible to know a priori. Not theoretically impossible, mind you. If you'd been smart enough and spent enough time thinking about it, you would have thought of them. But you aren't smart enough, and you don't have the time. Those are some other constraints that the universe puts on you.

[BiteCode_dev]

We spent 20 years talking about agile precisely because of this, and people took it, turned it into a checklist based processed, forgot about the short feedback loop it's precisely supposed to bring to the table to figure our your unknown unknown quickly, and declared it useless.

And now we are back to square one, where we argue again "but just make good specs".

The world is a silly place.