About

🚀 Founder of Pushary. Approve your AI agents from your phone. 😼 Building in public: ~300 users/mo, featured on Hacker News, top-4 all-time forum on the PH forums, only product forum in top 10 forums is Pushary. + Pushary: your agent needs a yes, it lands on your phone, you tap, it keeps going. Works with Claude Code, Codex, Cursor, and any MCP agent. + The unglamorous side of shipping a productivity tool solo: pricing, positioning, the launches that flopped and the ones that worked. + Charging from day one, no free tier. 🤖 AI agents 🔔 Push notifications 🚀 Growth ✍️ Build in public 💻 SaaS 💰 Bootstrapping Building too? Follow me here + try pushary.com. Collabs & integrations, DMs open.

Badges

Buddy System
Buddy System
Contributor
Contributor
Top 5 Launch
Top 5 Launch
Tastemaker
Tastemaker
View all badges

Maker History

Forums

our assistant agreed to something we do not sell, and the customer sent it to print

one of the shops we support does photo prints. someone asked if they also print diplomas. they do not. the assistant gave a vague answer, the customer asked again more directly, and the second time it said yes. they sent the file to print.

we sorted it out and nobody lost money, but the second answer is the part i keep thinking about. the first one was hedged. it only became a yes after the person pushed. so it did not really invent a product, it agreed with a confident customer.

Your agent does something wrong. How far does it reach before anyone notices?

Two months ago I asked here how people stay aware of what their agents are doing, and @getosmo replied with something that has been quietly rearranging my roadmap since.

I had been treating "can you undo it" as the line for when an agent should stop and ask. He took that apart. Irreversibility over-fires and under-fires, he said. It over-fires on things that cannot be undone but that nobody cares about, like the agent writing a log line. It under-fires on the ones that really hurt: a mass email to 50k users, or a migration you can only roll back after downtime. "Reversible on paper, ruinous in practice."

Do you actually let your AI agents run unattended, or do you babysit every step?

I run Claude Code, Cursor, and Codex most of the day, and I keep flip-flopping between two setups that both feel wrong.

Setup 1, babysit: I watch every command and approve everything myself. Nothing slips past me, but I'm stuck at the terminal and the whole point of running an agent is gone. I might as well be typing it myself.

View more