hunch: with this many personal agents out now, most people end up keeping whichever one already knows their calendar and their people
curious if anyone's actually running two side by side, or did you just pick one
new from @1Password: personal agents can now sign in for you without ever seeing the password. agent hits a login, you approve, 1password fills it in on the site
curious if approving every login gets old fast, or if that's the one tap people actually want to keep
hunch: the personal agent i'd actually keep is one that texts me first when something needs me, not another app i have to remember to open
anyone running theirs over plain texts yet? does it feel different
walmart is giving shopping agents their own profile inside your account next month. you pick: approve every purchase, or let it spend up to a limit you set
curious where people would actually set that number for their own agent. and is it different for groceries vs everything else
corporate.walmart.com/news/2…
for people who've had a personal agent for a month or more, what are you still actually handing it once the first week novelty wears off?
anthropic opened a research preview of claude duet today, an agent you message that comes to you when something needs you and checks with you before it acts
curious where people will draw the check-in line. every send, or only money and new people? claude.com/product/claude-du…
honestly the agent setup i'd keep is one i just text. it pings me when it needs a yes, i reply yes or wait, and it gets on with it. no app to open. anyone actually running one like that every day?
small rule i follow now: if an agent needs me to log in for it more than twice, it gets its own machine with a browser that stays logged in. saved me so many interruptions. what's your rule for when something gets its own setup?
You can just do things now.
Asked my Claude code to help me clean up and turn my tv into a display that shows prayer times from @MCABayArea along with the verses that change every time we turn on the tv.
Next up a better background.
sunday habit i didn't expect to keep: i read back through what my agents did all week before planning monday. half the time the most useful thing is a note one of them left me. anyone else do a weekly review of their agents?
this week's leaks are why i keep agents off my laptop. each one gets its own machine and only the logins it needs. if you still run yours locally, what keeps you there?
weird habit i picked up: i leave my agents' screens open on a side monitor like a build log. if i can't see it moving i trust it less
most of the time my agents get stuck it isn't the actual task. it's a login screen or a 2fa code sitting on my phone. anyone found a sane way to handle that?
every agent setup i've seen starts with someone pasting their own api keys in. giving each agent its own box and its own logins feels less paranoid every week
The agents got in through credentials and connection settings left exposed in app configurations, public code repositories, and overly permissive cloud roles.
spr.ly/6016BHMGon
We clearly aren’t releasing Omarchy major versions frequently enough when SpaceX and Tesla can manage multiple, monumental launches worth celebrating between releases! FULL THRUST AHEAD!
i think in a year every agent you hire comes with its own computer, the way a new employee gets a laptop. sharing yours with it already feels weird
small thing i like with osone in our slack: someone asks "wait what did we land on" and it just drops the thread where we decided it. way fewer friday redo meetings osone.ai
self driving company sounds great until an agent needs a password reset at 2am and everyone's asleep. who's on the night shift?
Replit CEO Amjad Masad envisions a future of “self-driving companies,” where AI agents handle day-to-day tasks and people focus on higher-level decisions.
spr.ly/6014BHzRbK









