Here's an example ticket that I'll probably work on next week:

    Live stream validation results as they come in

- What is the validation system and how does it work today?

- What sort of UX do we want? What are the specific deficiencies in the current UX that we're trying to fix?

- What prior art exists on the backend and frontend, and how much of that can/should be reused?

- Are there any scaling or load considerations that need to be accounted for?

I'll probably implement this as 2-3 PRs in a chain touching different parts of the codebase. GPT via Codex will write 80% of the code, and I'll cover the last 20% of polish. Throughout the process I'll prompt it in the right direction when it runs up against questions it can't answer, and check its assumptions about the right way to push this out. I'll make sure that the tests cover what we need them to and that the resultant UX feels good. I'll own the responsibility for covering load considerations and be on the line if anything falls over.

Does it look like software engineering from 3 years ago? Absolutely not. But it's software engineering all the same even if I'm not writing most of the code anymore.

This right here is my view on the future as well. Will the AI write the entire feature in one go? No. Will the AI be involved in writing a large proportion of the code that will be carefully studied and adjusted by a human before being used? Absolutely yes.

This cyborg process is exactly how we're using AI in our organisation as well. The human in the loop understands the full context of what the feature is and what we're trying to achieve.

But planning like this is absolutely something AI can do. In fact, this is exactly the kind of thing we start with on our team when it comes to using AI agents. We have a ticket with just a simple title that somebody threw in there, and we asked the AI to spin up a bunch of research agents to understand and plan and ask itself those questions.

Funny enough, all the questions that you posed are things that come up right away that the agent asks itself, and then goes and tries to understand and validate an answer, sometimes with input from the user. But I think this planning mechanism is really critical to being able to have an AI generate an understanding, then have it be validated by a human before beginning implementation.

And by planning I don't necessarily mean plan mode in your agent harness of choice. We use a custom /plan skill in Claude Code that orchestrates all of this using multiple agents, validation loops, and specific prompts to weed out ambiguities by asking clarifying questions using the ask user question tool.

This results in taking really fuzzy requirements and making them clear, and we automate all of this through linear but you could use your ticket tracker of choice.

I mean, what is the validation system? Either it exists in code, and thus can be discovered if you point the AI at repo, or... what, it doesn't exist?

For the UX, have it explore your existing repos and copy prior art from there and industry standards to come up with something workable.

Web scale issues can be inferred by the rest of the codebase. If your terraform repo has one RDS server, vs a fleet of them, multi-region, then the AI, just as well as a human, can figure out if it needs Google Spanner level engineering or not. (probably not)

Bigger picture though, what's the process of a human logs an under specified ticket and someone else picks it up and has no clue what to do with it? They're gonna go ask the person who logged the bug for their thoughts and some details beyond "hurr Durr something something validation". If we're at the point where AI is able to make a public blog post shaming the open source developer for not accepting a patch, throwing questions back to you in JIRA about the details of the streaming validation system is well within its capabilities, given the right set of tools.