◦ Prompt · Desktop

Give Your AI Agent a Front Door — Turn the Browser Tab Your Assistant Already Lives In Into a Native Mac App That Launches From the Dock, in One Session

Paste this into Claude Code, Cursor, or Aider and it interviews you about the agent you already run — what local server it lives in, which port, how that server is kept alive, whether it needs the microphone, and which Python built it — then does a strictly read-only pass over your project to see how your assistant actually starts before it changes a line. Only then does it wrap the browser tab you already use into a real desktop app: a chrome-less native window pointed at your own [localhost](http://localhost), a dock icon that's yours, and the three fixes that are the whole reason an embedded web view is hard — granting the microphone from inside the view so the orb isn't dead on arrival, making macOS attribute the mic prompt to your app instead of to Python, and routing OAuth and external-link pop-ups out to the real browser so sign-in doesn't silently vanish. It adds a splash screen that wakes a sleeping server and waits for it, then bundles everything into a signed .app that lands on the dock and survives a reboot. Interview first, map second, then build tier by tier — each tier launches something you can see and is verified before the next begins.

Jul 22, 2026agentdesktop-appmacoswkwebviewpywebviewtaurivoice-uipackagingtutorial
◦ 5,212 builders waiting

Want the agent behind these prompts?

These prompts came out of building Trillion. The whole thing is going open-source on GitHub. Drop your email and I'll ping you the moment the repo drops.

I'll send a one-time link to confirm your email. Nothing else.

◦ Next prompt
Give Your AI Agent a Scout — From Hard-Coded Prompts to Operator-Tunable Doctrine in One Session →

Paste this into Claude Code, Cursor, or Aider and it'll walk your agent codebase through building a scheduled scout sub-agent: a research loop that ends in a validated structured report, an evidence-first rubric with explicit hard kills, rotating hunting lanes that change what it looks for by the day, a review pipeline where a human decides and the agent never does, and — the part almost everyone skips — an instruction set that lives in editable documents your operator can retune from the UI with override, revert, version history and hot reload, instead of a Python constant nobody can reach without a deploy. Interview first, then build tier by tier. Each tier ships independently with verification.