◦ 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

◦ 4,329 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.

◦ Next prompt

Give Your AI Agent a Board of Advisors — Turn Well-Documented Operators Into Seats That Actually Disagree With You, Cite Their Sources, and Refuse to Answer When They Don't Know, in One Session →

Paste this into Claude Code, Cursor, or Aider and it interviews you about the agent you already run — what it can read about your business, how it surfaces things to you, whether it can schedule its own work — then researches each advisor you name, fact-checks that research against itself, and builds the machinery: one markdown dossier per seat holding numbered, citable doctrine; a router that picks who has standing on a given question; a fan-out that gives each seat its own isolated model call so they can genuinely disagree; a citation gate that strips any reference a seat could not have seen; and your own agent as chair, the only participant who has read your actual revenue. Plus abstention as a first-class answer, a unanimity guard that cannot be talked into agreement, blind spots that let the chair discount a seat, and a standing monthly review that puts an agenda in front of you without being asked. Interview first, research second, then build tier by tier — each tier produces something you can run, and the anti-fabrication defenses are built before the first meeting, not after.