It's not from a few prompts, you're right. But if you layer on some follow-up prompts to add proper test suits, run some QA, etc... then the quality gets better.

I predict in 2026 we're going to see agents get better at running their own QA, and also get better at not just disabling failing tests. We'll continue to see advancements that will improve quality.

I think someone around here said: LLMs are good at increasing entropy, experienced developers become good at reducing it. Those follow up prompts sounded additive, which is exactly where the problem lies. Yes, you might have tests but, no, that doesn't mean that your code base is approachable.