I'd substitute "owner" for the team and in that sense the owner will not need to be human.

We're at this state where Claude is great at doing the "middle" part of work, but it's crap at gathering requirements and verification of what it has done. I also don't see people caring about these aspects of software development as shown in the article

But yes, you are right - I don't build roads and don't know what is a price to build a road and how to determine the quality of correctly built one, nor I will ever care or learn.

These questions are even not about AI: if I were to give money to a human agency and were given something they tell me works, I would ask the same questions. If I did not know how to evaluate, I would hire people that do. With LLMs the verification part is what bothers me the most.

- show increase in errors and outages caused by this approach

- integrate manager changes into your CI pipeline (coding / reviewing / testing / documentation)

- discuss how your manager can do the changes they need to do without sidetracking all other work

Make it indeed about the money: coding by PM + fixing what was coded + dealing with fallout is greater expense than coding by PM + automated guidelines + reviewing what was coded.

That is - if the environment you're working in is reasonable and it's not a power play by your PM

Why are you allowing AI rockstar managers to (I assume) push without code review? Why are you cleaning up the fallout? It's not AI issue, it's people issue

Domain expert can develop working code, but they will not be able to ensure above.

Still Claude will sneak things in - in my recent plan, for example I had defined, per acceptance criteria what colours the statuses should be: green for live, blue for sold, grey for anything else; it changed this to: green for live, orange for in progress, blue for sold, red in demolition, etc. When pressed why did it to this, it was unable to explain why. This is with a plan where AC were explicitly provided from the task in Given/When/Then format and were to be adhered to strictly. I've caught this within planning, but I shouldn't need to be doing this.

Even in standard prompts where I tell it "Change this label from X to Y", it ended reordering the tabs unrelated to ask. Again I was not able for it to explain why - it was so abrupt. And it was in fresh context, without any pollution on what I expect it to do.

I also noticed a different behaviour regarding skill; today and yesterday it would not be following skill guidance at all ie: skill writing skill - I'd have to explicitly tell it to test skills after writing them, when this is a behaviour expected by default. Similarly with other skills - knowing that it should have done something per skill guidelines and it not doing it at all. This is new behaviour that I've not seen a week ago.

Webdev here, but currently I have: - a skill where I outlined how the architecture of the system should look like, with guards (static analysis, architecture tests, linting) confirming that the code it generates adheres to standards

- a skill that tells it how tests should look like (use generators, write both feature / unit tests)

- a skill that tells it to generate docs from the code in a form of acceptance criteria (Given / When / Then)

- a skill that tells it to generate frontend uat tests + accompanying backend seeders given the AC

- a skill that tells it to verify that ticket objectives match what was delivered

At this point I still need to guide it to move task from one stage to the other (coding, testing, verification that indeed what was coded adheres to what was required), but I believe that these dynamic workflows can automate this work as well.