A lot of devs still think their job is to produce code; it's actually to produce all of the guidance and structural scaffolding for the agents ("the harness") to guide its behavior and output.
A concrete example: I wrote a small library[0] (MIT, OSS) that improves how agents write unit and integration tests. This isn't product code, but this makes the agent better at writing the tests it uses to verify its work. (Tests become denser, more semantic, less context, type-checked setup, etc.). You can't expect an agent to do this by itself; the human needs to produce the scaffolding.
i have written alot of this type of documentation as an architect for human teams, and i find it works for agents as well.
This basic reasoning is wrong and leads to “orchestration porn”. Thinking that you can laid down rules to automate software production like it’s a factory pumping out product.
What you forget is that software are grown iteratively, not guided down some assembly line. Every patch is a revision of what the software should do, not the next step od a workflow.
So stuff like patterns, architecture, tests,… are helpers for communicating the purpose of the software. They’re not really relevant to the software itself as the computer would be happy with just a single file.
You have a software that’s needed to fulfill some needs, you have a team of people where each brings expertise to build it. Workflows are built so that everyone how to contribute, what they can depends on, and what others need. When there’s a failure, we add the missing information. When there’s need to do some changes, we inform everyone impacted.
Everything is information and communication related. Information about the system and communication between everyone that interacts with the latter.
So devs do not think their job is to produce code. It is to take requirements written in ambiguous natural language, sometimes incomplete and contradictory, and to design a solution that is formally written while taking care that all statements are coherent.
Making things coherent (aka correct) is what takes the majority of our time. The other is gathering requirements. The actual typing of code is pretty much instinctive, just like you don’t check the orthography of words like “concrete” or “guide”, and rely on the spellchecker for more difficult one.
The “orchestration porn” part is that there’s no mention anywhere on how you think correctness and be improved or even maintained as part of your tool.
AI agents don’t have this in a sense; or they do, but it’s average and stochastic. We have to be in the loop to provide judgement and manage the agent’s context; the content of that context steers the agent in the direction that our judgement tells us the development should go, to meet the various requirements. Some of those requirements are around the software’s function, some around maintainability, some around understandability, etc.
I think scaffolding is good at decreasing the amount of repeated mistakes and ensuring the agent can request and receive information efficiently. I think software factories are too self-referential; I’m not set on that opinion though and like I’ve said in another comment, I will fall down this rabbit hole at some point just to see what it’s like.
So many times I’ve wondered “you know how to do this, so why didn’t you just do it the first time?” — the old “Oh you’re absolutely right! That’s a much better way to do it!”.
It’s not that the model doesn’t have the knowledge, it’s that it doesn’t access it at the time it is needed. Part of my job now is to collaborate with the models and the tools.
The first is solved by deterministic tool as code is already formal, so the grammar is very strict and fully defined. But the second part is entirely human dependent of what the end result should look like, even when the same semantics is being kept. That's why two people asked to implement the same task will code it differently even if from the point view of the machine, they're equivalent.
Maintainability and readability is not about software correctness. It's about how the human mind can absorb what the software should do, aka the specs embedded in the code, which is just formal notation. If it's easy, then the software correctness is easy to check and validate. And when the requirements changes, it's easy to apply the needed modifications.
So asking agents to improve upon that is like asking an agent to write an email. It's an alienation of human-human communication.
> there’s no mention anywhere on how you think correctness and be improved or even maintained as part of your tool.
The first paragraph is literally a list of examples, followed up by a specific library that helped the OP. The paragraph you quoted explains where the maintenance lies.
Building "orchestration" without being able to deterministically measure improvements is not engineering, it's cargo cult.
You have to stop thinking this way. It's our job to do what our management wants us to do, which is often to produce as much software at the lowest cost possible.
There are legitimate criticisms about AI use and how AI has changed the profession, but you have to learn which battles are worth fighting.
Personally, I was asking "but what's the use case" in every meeting. "Why would somebody pay for this". "Who's the customer". Right now the vibes are quite similar to back then.
The refusal to take responsibility for the consequences of one's work is one part of a vast complex of machines that normalize the horrific. We have met the shoggoths and they are us.
Have you ever been in a situation where you did what the management wanted you to do for years, regularly warning them that you could not write good code while doing what they wanted but being dismissed because they knew better? And have you ever been in a situation where you finally got your "I told you so" moment after years, when they actually realise it won't work?
I have. You know what happens then? It's not their fault. Best case, they explain why you couldn't have known better because it was hard. Worst case, they fire you because... well you built that mess, remember?
Damn if only there was a way to write strict rules and patterns in the english language that could be converted into strict instructions for the computers and ways to verify those instructions...
I've seen it first hand. 70 people fired, 20 people left. The 20 that are left take on all the work that was done before, plus some extra, because every company now has a new AI product, obviously. AI agents make us so productive. Every review is a 30 second LGTM on 500 new lines of code. Confluence filling up with AI slop.
A few weeks back I saw, first hand, a DevOps lead getting ready to ship a big update to performance-critical product where Opus 5.5 suggested they completely turn off JIT everywhere because they were running into a HotSpot C2 optimizer bug that would make the first request after a restart fail with a 500. Actual fix was a one-line adjustment somewhere in a library.
People are scared of being replaced, so they need to appear as productive as possible.