Questions

It stays with you. Editions, receipts, and the notes you wrote belong to your Rovyn account rather than to the assistant that was connected when you made them — so a new assistant, granted the same permission to read receipts, reads the same history from its first question. Disconnecting the old one ends its access and deletes nothing: the editions it built stay on your shelf, still under its byline, because it did edit them. Your taste profile lives with you; every assistant borrows it.

Yes, and they don't collide. Each connection is its own grant with its own permissions, added and withdrawn on its own — one assistant for the long courses and another for the commute, if that's how you work. They write to the same shelf and read the same receipts, and every edition carries the byline of whoever built it, so you always know which editor you're arguing with.

Because your Rovyn account is where the editions land, and the account is simply whichever identity you signed in with. Sign in to the connector with Google and to the iPhone app with Apple and you have two Rovyn accounts — your assistant building editions into a library your phone isn't in. Accounts can't be merged afterwards, so the choice worth a second of thought is the first one: pick Apple or Google and use it at both doors. Connect says it again next to each assistant's steps.

The honest answer is what Rovyn asks for and what Rovyn hands back — a scoped brief goes out, receipts and your own words come back. The brief is what your assistant states about the request: the goal it's building for, plus whatever constraints you gave it. Rovyn doesn't ask for your chat history and has nowhere to put it — the brief takes a goal, the time you have, a level, and preferences, and anything else attached to it is dropped at the door rather than stored. You can read the brief on the edition it produced. What returns is per episode: finished, partly, or skipped, roughly how far and how long, and any note you wrote, passed on as you typed it rather than summarized or scored.

Raw playback events stay server-internal — there's no tool that returns them — and a connection reaches only what you ticked at the consent screen: reading plans, writing plans, reading receipts, and writing feedback are four separate permissions, each revocable on its own. The privacy policy has the specifics.

Any assistant that speaks MCP can connect, and four have step-by-step instructions on Connect: Claude and Perplexity on their paid tiers, Grok for all users, and ChatGPT through developer mode on a paid plan. Gemini is narrower — custom MCP apps are a Spark feature on the Ultra tier — and a listing in ChatGPT's directory is in review, with no date we can promise you. The assistants move their own doors often, so Connect is the page kept current; this one would only tell you where things stood the day it was written.

Because something already does, and it has a chat window where you can say what you actually want and correct it when it's wrong. Where every other podcast app puts Discover, Rovyn puts an empty shelf, waiting for what you ask for. A recommendation engine underneath that would only be a second opinion nobody asked for, quietly competing with the editor you chose.

That's the design. The backend is a single service, and the protocol it speaks is Cueback — open, media-neutral, and specified apart from this app, so a Rovyn you run yourself has the same privacy properties by construction rather than because we behave well. Honest about today: the specification and the self-hosting guide are still being prepared for publication, and until they are up the docs page is a stub. If you're building against Cueback now, write to support@polimati.com and you'll get the current spec.

Nothing at the moment. The iPhone app is in TestFlight until launch and invites go out by email, usually within a day — write to support@polimati.com and you're in the queue. The one cost that isn't ours: several assistants keep custom connectors on their paid tiers, noted per assistant on Connect.