Pushary for Teams - See who said yes to your team’s AI agents
by•
When an AI agent stops to ask permission, Pushary sends the question to the person running it, in their Mac’s notch or on their phone. Lee’s agent asks Lee. Sam’s agent asks Sam. A rule can send a push to your infra repo to your lead instead. Answers from the phone, Mac app and dashboard are saved with a name, so when something breaks, one page shows whose agent asked and who said yes. Works with Claude Code, Codex, Cursor, Agy and Hermes.
Replies
Hey PH 👋 Aadil here.
Pushary shows your AI agent's permission prompts in your Mac's notch, and on your phone when you're away from it. Today it does that for a whole team.
Tom's Cursor asks to push to main. He says yes in his terminal. Twelve minutes later prod is down, and the first question in Slack is "whose agent pushed this?" Nobody else saw the question.
When it's just you, you know who said yes. Once two or three people run Claude Code, Codex or Cursor on the same code, nobody does. Each agent asks whoever is at that terminal, and nobody else ever sees the yes.
On our July launch, Ridhwik put it best: "If my agent drafts an outbound email, the real approver should sometimes be my marketing director, not whoever paired the phone." Eight of you asked for the same thing. So we built it.
With Pushary for Teams:
When something breaks, one page shows whose agent asked and who tapped yes. The Friday retro takes one page, not an hour in git log.
Then add one rule, like "pushes to infra ask the lead first", and next time the lead gets that question.
Every agent asks its own person, in the notch at the Mac and on the phone when they're away. Nobody gets the whole team's questions.
No scores, no leaderboard. Everyone sees the same page.
Honest bits: If you work alone, Claude Code and Codex already let you approve from your phone for free. Use that. Pushary is for when several people's agents need one record, across vendors.
Try it: pushary.com/teams
One command for each person, then scan a QR code with your phone. $59 a month for 5 people, 3 days free for new workspaces, and PHTEAMS takes a month off.
For today: reply with the one command you'd never let an agent run without a second person, and I'll reply with the rule that sends it to them.
And if Pushary has helped you before, a one-line review would mean a lot. We have exactly one.
I'll be here all day <3
@aadilghani How does Pushary handle conflicts when multiple agents work on the same codebase?
@shivam_kushwaha16 when you install Pushary, the skill automatically tells your agent to work on its own worktree whilst managing disk space.
this way multiple agents working in parallel do not break your codebase.
feel free to test it and let us know how you like it.
looking forward to welcoming you as our user!
@aadilghani
Guys, congratulations on the launch! Best of luck to you.
What happens if two people approve conflicting actions for the same agent at almost the same time?
Congrats @aadilghani & team!
Thanks for sharing @rohanrecommends :)
@rohanrecommends @hamza_afzal_butt it runs in a transaction, meaning the first approval recorded is taken into account and logged in your audit log.
give it a shot and let us know how you like it, looking forward to welcoming you as our user!
@hamza_afzal_butt KING!
Now, we have an overview of who made the AI agent competent :D and who will be responsible for things when they go badly :D
@aadilghani I cannot name one specific one, but probably those where their workforce hasn't been replaced by AI agents, but only to some extent. So not solo founders :D
@busmark_w_nika exactly
our agent plans already support hundreds of solo founders.
teams is to help agents and human teams collaborate better with a record of who approved what for accountability.
love your input here and looking forward to welcoming you as our user! 🫶
@rukhsar_amjad
you can set different approval rules and also route to the right person for specific tasks, give it a shot and let us know how you like it :)
@aadilghani How do you ensure that agents don’t receive more permission than they actually need ?
@dipanshu_kushwaha5 this is actually a smart question, we have the Pushary classifier that is installed when you get our mac app or install us via cli, then it asks you exactly the questions that are risky.
cool part is, you can customize this and define your risks so it only asks you the questions that make sense for you and your team.
Give it a shot and let me know, looking forward to welcoming you as our user!
We are using already in our team btw
Of all these notch related apps we've seen recently, this one looks like it might actually be useful. I'd need a longer trial to be sure though - something to consider.
@simon_moxon one month sound good? use PHTEAMS coupon in checkout.
I'm happy to guide you and your team through the full setup personally on a call https://cal.com/aadilghani/pushary
I love the permission monitoring capabilities this brings to larger teams and swarms of agents.
What does the agent do while nobody answers? If the person it's routed to is asleep, does it time out and deny, or just sit there holding the session?
the "whose agent pushed this" question in slack is too real, the yes in someone's terminal just dissapears and nobody can find it after
the one i'd route to a second person is anything that emails customers from a prod account lol. can a rule match on what the command actually does, like a curl to a mail API??? or only on repo and path???