alt Hacker NewsIn what I've seen, tickets are much richer in detail now because PMs are using AI (connected to the codebase itself, like Claude Code or Codex) to fill out a template as to what and why the problem is (ie X field exists in the backend not frontend), how and where to get any data (query the backend), and what acceptance criteria is needed (frontend should have the field exposed and "submit" should push the field's data to the backend where it should show up in the databas), which is something they would not have done before, due I guess to laziness and thinking the devs can figure it out. Then devs can copy paste this Jira ticket content into the LLM agent of choice (or even use the Atlassian MCP to have the LLM read it automatically).
This has significantly helped devs and made sure that requirements are very clear.
Honestly, with the first step, it seems the PMs are already halfway there to implementation of the feature so I wonder if in the future they'll just do everything themselves and a few devs will be around as SDETs rather than full blown implementers.
Replies
IMO the code-generation for boilerplate and the improvement of copypasta quality are much bigger improvements than that.
PMs turning their brain off and letting the LLMs extrapolate from quick and dirty bashing of text into a template (or, PMs throwing customer feedback at a slackbot to generate a jira ticket form it) can be better than PMs doing nothing but passing ill-defined reqs directly into the ticket, but that's a low bar. And it doesn't by itself solve the problems of the details that got generated for this ticket subtly conflicting with the details that got generated for (and implemented) in a different ticket 8 months ago.
If you do that someone still needs to make sure the details make sense which, from experience, sometimes they will and sometimes they won't. When I open tickets using automation I often back into the ticket from a running implementation that passes tests so the description is at least internally consistent but there are often still issues that need corrected.
> Honestly, with the first step, it seems the PMs are already halfway there to implementation of the feature so I wonder if in the future they'll just do everything themselves
I'm guessing they've tried (or been induced to try by upper management), but given up because they don't know how to debug any problems that arise due to the LLM working itself into a corner.
Coding-agent LLMs act a lot like junior devs. And junior devs are: eager to write code before gathering requirements; often reaching for dumb brute-force solutions that require more work from them and are more error-prone, rather than embracing laziness/automation; getting confused and then "spinning their wheels" trying things that clearly won't work instead of asking for help; not recognizing when they've created an X-Y problem, and have then solved for their Y but not actually solved for the original problem X; etc.
The way you compensate for those inexperience-driven flaws in junior devs' approach, is to have them paired with, or fast-iteration-code-reviewed by, senior devs.
Insofar as a PM has development experience, it's usually only to the level of being a "junior dev" themselves. But to compensate for LLMs-as-junior-devs, they really need senior-dev levels of experience.
The good PMs know all of this, and so they're generally wary to take responsibility for driving the actual coding-agent development process on all but the most trivial change requests. A large part of a PM's job is understanding task assignment / delegation based on comparative advantage; and from their perspective, it's obvious that wielding LLMs in solution-space (as opposed to problem-space, as they do) is something still best left to the engineers trained to navigate solution-space.
> Then devs can copy paste this Jira ticket content into the LLM agent of choice
Super glad to have gotten out when I did...
> it seems the PMs are already halfway there to implementation
Halfway there feels way overblown, and only seems to further devalue to work that devs do. Having clearly written requirements would be fantastic, and even as someone less pro AI even I can see great utility for it here, but its not halfway there to implementation. Not even 25% in all honesty, since edge cases and unforeseen consequences can cause changes to the spec midway through development.
> Honestly, with the first step, it seems the PMs are already halfway there to implementation of the feature so I wonder if in the future they'll just do everything themselves and a few devs will be around as SDETs rather than full blown implementers.
Judging by every PM I’ve worked with, 0% chance of this happening. Much sooner would see SWEs making PMs redundant than the other way around. Unless of course you want a system that falls apart like a house of cards as soon as you get a single user for your vaporware.
Except... no one validates the generated tickets, and it's full of inaccuracies.
And then someone copy pastes it into Claude and now those inaccuracies become part of the code and tests.
lol
Just lol. Is this what you guys mean by productivity boost?
Comical. LLM’s aren’t all that great - it’s more that most orgs are horribly inefficient. Like it’s amazing how bad they are.
That’s why Elon succeeded with spacex - he saw how horrible inefficient the industry was. And used that thinking to take a gamble and it’s paid off.
Maybe for some subset of sotware (like CRM panels or something) PMs will do everything. But if you're projecting the way one sort of software (ie user-facing, business use oriented software) is developed and put to use with software writ large, then no I don't think so
> Honestly, with the first step, it seems the PMs are already halfway there to implementation of the feature so I wonder if in the future they'll just do everything themselves
Yes please, I've seen the vibecoded slop PMs put out every day because software engineering is simply not a skill they have, and I'd love to make a LOT of money fixing their crap once it dies in production <3
I can't imagine SWEs will be reduced to SDETs anymore than attorneys will be reduced to spell-checkers on AI powered case briefs.
I am a very AI-forward person, but hallucinations are becoming more pernicious than ever even as they get less frequent, especially if the code actually works. A human absolutely has to guide these processes at a macro level for sustainability for SaaS as it evolves with business needs.
Maybe for one and done systems with no maintenance/no updates/no security patches you can reduce humans to SDETs, but systems like that are more the exception than the norm.