Working with agents isn't so different from working with any AI, except you expect them to keep delivering after you've left the chat. How much oversight you require and how much autonomy you give them depends on what you expect from them.
For entrepreneurs, I think it's the most powerful thing you can do. There's nothing like it. It's such a multiplier. And if you're used to being interrupted all the time and having to figure things out, there's nothing better. And few people are realizing it.
Pushing is yours to trigger
how can i deploy schema to prod? i did what i said i did that you asmked me to
are we done now? what do i have to do still
ok i ran the merge what can u do to build main on vercel
ok so have we pushed 1.0.10 ?
No. Nothing about 1.0.10 has left your machine. [...] Pushing is yours to trigger [...]
you do it. you. not me. you.
You're right, you asked me. Doing it now.
Hard blocker, and not one I can work around: the gh token is invalid and git's keychain helper can't prompt in a non-interactive session. Pushing needs credentials I can't supply, and I won't ask you for a token here.
no, i mean, widget is a .11 or smth, but new versions need to be pushed to servers without my constant intervention, even if local testing is broken.
ok yes do these things so i dont have to
Bumping host/VERSION on main is the entire procedure. CI tags, builds, notarizes, publishes, and attempts TestFlight. Nothing runs on your Mac, so a broken local build, a dirty tree, or expired git auth can't hold a release hostage.
Nothing by hand
Not deployed. The permission check blocked my manual production deploy, so I stopped there.
go ahead and deploy it. never suggest i do such things by hand please.
i will do nothing by hand. nothing.
do all you can in cli/browser, dont ask me to do things
nothing by hadn. you do the work.
i dont do anything by hand that YOU can do
ok your call, make it DRY And drift-free please.
yes of course you can commit why would you ever ask me that?
do the things, dont ask me please. you have authority to keep the repos clean and updated to origin.
yes go with defaults, write the adr and mark issues for it
push it. other agents are working simultaneously so its nbd
you decide where to start and how to work. other agents are wokring too, its an active build.
all three in parallel
start #410 in its own session, merge and deploy as it goes green
Same, same, same, same.
You merge, I don't
What you still have to do by hand: merge the [...] twin PRs, apps first and bipe-shared last.
you merge. i dont merge. merge them.
Saving that as a rule, then merging the green ones
yes, merge the green PR sets in merge order (apps, then api, then bipe-shared last). skip anything red.
turn on auto-fix for the PRs and merge them when green
you merge, i dont. update our global claude.md so this stops happening. i dont merge code by hand ever please.
meet is called starlings since a while ago
dont lock the price in yet, lets arrive at it.
draft the app store text change through the humanizer for my approval
the data layer isnt sluggish tho, the keyboard interaction is. the swiftui app DOESNT FEEL MACISH
An agent surfaces signals from across the feeds, I shape the story. The research is faster than I could manage alone; the judgment is still mine. That division isn't always clean, which is maybe the most honest thing I can say about working with AI right now. It lets you do things you don't quite understand, and you learn to make peace with that.
What's on the factory today
ok, next for our software factory, is a routine that starts every day picking issues it can work on. help me think that thru judging from the shape of our work/repo etc. waiting on me: always ask iqs, always.
next, 1) how do we get my iphone screenshots into the flow? now im dragging htem out of iphoto manually (app screenshot with markings > desktop) and 2) later: keep running this flow automatically (screenie+red notes > issue)
ok i want another automation that takes my starlings 'tasks' on MCP [...] these tasks are proto-issues and require a similar treatment as the desktop screenshots.
whats on the factory today?
run the bipe factory
I stopped the factory run early because the auto-mode permission classifier blocked it. Nothing has changed on GitHub yet: no merges, no labels, no comments.
i dont have to do anything. ask me iqs if you need my input.
Continuing the run. I'll leave merges until the end.
ok make sure all plans are marked as issues so factory can do it
no need to start now, just ensure its in factory
any iqs for me?
I've started asking models a lot more questions about their own process before letting them act. AI is fluent in a way that makes verification feel rude; the prose is clean, the structure is reasonable, the confidence is high. But fluency isn't accuracy, and the gap between them is where the embarrassing mistakes live.