Yes, I ran into the same problem last week. But I just said "this is my code in a private repo" and then it just went and did what I asked without question.
I look at my ticket tracker and I see basically 100% of it that can be done by AI. Some with assistance because business logic is more complex/not well factored than it should be, but most of the work that is done AI is perfectly capable of doing with a well defined prompt.
Using an agentic workflow does not require you to delegate tge thinking. Agents are great at taking exactly what you want to do and executing. So spend an extra few minutes and lay out the architecture YOU want then let the ai do the work.
I've had success here by simply telling Codex which components to use. I initially imported all the shadcn components into my project and then I just say things like "Create a card component that includes a scrollview component and in the scrollview add a table with a dropdown component in the third column"...and Codex just knows how to add the shadcn components. This is without internet access turned on by the way.
Right. The idea here is to kick of 3-8 or something tasks. They finish as you finish writing the next prompt. Then you go and review/test/merge the code from the first task, then another task finishes and you review/test/merge that code.
The challenge is that you have to be working on multiple work streams at once because so far Codex isn't great at not doing work you are doing in another task even if you tell it something like "class X will have a function that returns y"...it will go write that function most times.
I've found it really good for integration work between frontend and backend features where you can iterate on both simultaneously if the code isn't in the same codebase.
Also, for Codex this works best in the web ui because it actually uses branches, opens prs, etc. I think (though could be wrong) that locally with the CLI or IDE extension you might have to manually great git worktrees, etc.
Because you'll be replaced by those engineers in N months/years when they can outperform you because they are wizards with the new tools.
It's like failing to adopt compiled code and sticking to punch cards. Or like refusing to use open source libraries and writing everything yourself. Or deciding that using the internet isn't useful.
Yes, developing as a craft is probably more fulfilling. But if you want it to be a career you have to adapt. Do the crafting on your own time. Employers won't pay you for it.
I've had a chevy volt since 2014 and it's amazing at this. 30+ mile range gets me all the local travel that I need daily plus the gas range makes roadtrips completely stress free since I can just go get gas.
At HomeLight we migrated from Heroku to Porter and it has been great. The team has been super helpful, the platform as stable as you can get, and the cost savings have been tremendous.
I’d highly recommend Porter as the place to go to get started these days. I don’t see any reason that we will migrate away in the next few years, if ever.
I ride a public bus from oakland across to SF a couple mornings a week (used to be every morning before covid) and that trip is basically like this. 3/4 full bus, no one standing, good cell coverage most of the way.
Shortcut maybe? It's definitely not the same exactly and I haven't used PL in a ton of years, but I think it works pretty well overall. The general organization is Milestones -> Epics -> Iterations -> Stories