@kentcdodds A most of the time, B probably won't even be off the ground by the time A is completed, and B will still have bugs and issues just like A but with a much slower fix rate
What we have been doing in my company, which I got inspired by your prototype skill and your grill me with docs skill is:
The PM makes a prototype with claude, once done a spec-grill skill goes over it, it infers as much as possible and start working with the PM on the spec, once done the prototype is tagged in the spec and the PM opens a PR, important part the spec have no technical wording is not a implementation plan in plainly AC and product information, from there the developer takes over.
The spec is maintained you can change the core as much as you want as long as it accomplishes the same goal from the spec.
Is not a perfect flow, for sure but is much better than plain Jira/linear tickets(this way of working makes no sense at all btw in the agentic era)
I have been able to finally got to I point where I trust my agents enough after giving them the tools they need to succeed
At the same time I have never felt so out of place in my life, I have no one to talk about at all even people I admired feel like they are behind now #ai
@theo@theo another idea that goes from this, code should have filter for these kind of files! That is really helpful if you actually want to check out the code!
@poteto I totally agree, I added some extra rules around it so it would follow my workflow in my workplace and it is amazing!
I also using t3 code with it hehe
something that keeps bothering me is how some people see slop as something that is happening to them, like they're some kind of helpless bystander powerless to do anything about it
excuse me but you are a software engineer, you literally learned how to make sand think and make computers do your bidding?! and now you can't do anything about it? please
the 2 things you should know to cut through all the noise:
1. you need to give your agent a way to verify its own work (i just posted about this so won't rehash)
2. your codebase is memory
the 2nd is not new either, we have always had lint rules, compilers with good diagnostics and strong type systems, LSPs, etc to help us write better code. there is no difference when agents write the code instead, you just need more of them, and stronger ones.
forget rules and skills. you can add those later.
yes, your codebase is a form of memory to agents! agents love extending what already exists. so every nit and every annoyance you've ever seen, every mistake and bad pattern you observe from agents, needs to turn into a constraint, or the agents will just keep repeating those same mistakes like a virus in your code. then you keep observing and repeating this process until your codebase is locked down enough that even agents with little context can one shot a high quality PR.
an even better direction is to refactor/rewrite your code such that agent anti-patterns become categorically impossible. use type systems to your advantage, use libraries/frameworks that reduce the architectural search space, or heck, create your own framework like we did for grok bot and design high quality primitives and well thought out APIs