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
Thought Leader
Thought Leader
Top 5 Launch
Top 5 Launch
View all badges

Maker History

Forums

When did you last say no to your AI agent?

After enough "can I run the tests?" prompts, "can I send this to your customer?" risks becoming another button to clear.

Five months ago I asked here how people keep track of their agents. The replies went well beyond coding. In a later discussion, a builder running customer support agents made a point that stuck: people stop reviewing when checking the draft takes longer than writing the reply themselves.

Go check your terminal. How long has your agent been waiting?

Open the terminal where your agent is running. Do it now, before you read the rest.

Is something sitting there waiting for you? How long has it been there?

What if the cheapest way to reduce AI costs isn't a cheaper model?

We keep talking about AI agent costs as: model price tokens requests

But agentic systems add another cost: uncontrolled execution.

  • An agent retries a tool 5 times.

  • Calls an expensive model when a cheaper one would work.

  • Loops through unnecessary steps. Hits APIs it didn't need.

  • Delegates work to another agent.

View more