Sources
A twin answers from your sources and nothing else. This is how material gets in.
Where this lives
Knowledge is three panels, and they're listed across the top of the page whichever one you're on:
- Sources — everything your twin has learned from, what state each one is in, and a way to remove any of them. Past eight sources you also get a filter on title and type, because a list you have to scroll is a list you stop checking.
- Add — the ways in below, plus bulk import.
- What it knows — the summary your twin writes from your sources, and the box for correcting it.
The sidebar also lists the three underneath Knowledge while you're on it, when the sidebar is showing names rather than icons — that's a shortcut to the same three places, not the only way to reach them.
Each panel has its own address, so the one you use is linkable and
bookmarkable: /app?view=knowledge&panel=sources, …&panel=add, and
…&panel=base. A plain /app?view=knowledge link — including every one you
saved before the panels existed — still works and opens Sources. Buttons that
mean add something take you straight to Add.
Ways to add material
Paste — the fastest start. Drop in text and it's stored immediately, and answerable from the next train.
A blog or a site — give it a URL and it reads the pages it finds there.
YouTube — it uses the transcript, so a talk you gave becomes something your twin can quote.
Files — documents you upload.
LinkedIn or a CV — the fastest way to give a twin your background.
Bulk import — several sources at once, when you're starting from an archive rather than a blank page. Point it at a blog or a YouTube channel, pick what you want, and the import runs on our servers: you can close the page as soon as it starts, and it will finish, rebuild your twin's knowledge, and be there when you come back. If a page or a video can't be read, that one is listed with the reason and the rest still come in.
An assistant's memory — the facts ChatGPT, Claude or Gemini already hold about you, pasted in and reviewed fact by fact. It answers questions but never shapes your twin's voice.
Starting from nothing — until your twin has its first source, your Overview opens with four starting points rather than a list of instructions: import a page you wrote, paste something you wrote, upload a PDF or a doc, or bring what ChatGPT or Claude already knows. Each one opens into a single field and adds the source from that page, so the first source never depends on finding this tab. They go away as soon as one exists.
What happens after you add one
Adding a source doesn't rebuild your twin on the spot. The source is stored and counted straight away, and it joins what your twin knows at the next train. Until then the twin keeps answering from the material it already had — adding something never takes a working twin offline.
Trains run overnight by themselves, in your own timezone, and gather up everything waiting into one rebuild. You can also start one whenever you like from Train → Train now, which takes minutes rather than waiting for tonight. Nothing is lost in between: the queue just grows, and the Train stage shows how many changes are in it.
The first source is the exception. A twin with no index yet can't answer anything at all, so its first material is built immediately rather than waiting for the night — you add it, the page comes back, and it is answerable. The message you get on adding always tells you which happened, so you never have to guess.
While a change is waiting, the row carries a Waiting chip and asking about it can still get an honest I don't know. The chip clears when the train lands. Bulk import is the one thing that still rebuilds by itself: it runs on our servers and trains once at the end, because "import this archive" is already a batch and splitting it across two waits would help nobody.
A source you untick in Train reads Held back instead, and keeps reading it until you tick it back on. Held material stays in your list and stays out of every train — it is not waiting for anything, and it costs nothing against what your plan holds. Ticking it back on puts it in the queue like any other change, so the next train picks it up.
A source with no chip is live and answerable, which is most of your list most of the time. That's why the settled state is the one with nothing to say: a badge on every row would be furniture, and the state worth interrupting you for is the one where your twin can't answer yet.
Removing works the same way, and that matters more. A removed source reads Removing and leaves the index at the next train — until then your twin can still answer from it. If you need it gone now rather than tonight, remove it and then press Train now; that rebuild is what actually takes the material out.
Removing is never paused. Your plan includes a number of trains a month, and running out pauses the overnight ones — but never a train that is taking something out. A source you delete leaves the index at the next night whatever your month looks like, and Train now stays available for it. Taking your own material down is not something you can run out of.
Deleting the last source empties the index and takes the page off the air at the same time — at that train, not at the moment you press delete, so a twin you have shared keeps answering until the rebuild lands.
Your material trains your twin alone. Never a shared model, never someone else's twin, never sold.
If a rebuild fails
Rebuilds retry on their own, and most problems clear themselves. When one runs out of retries, Knowledge says so at the top of the page: Last rebuild failed, when it happened, and — the part that actually matters — the date of the index your twin is still answering from.
Nothing is lost and your twin does not go offline. The previous index keeps answering the whole time, because the swap only happens at the end of a build that worked. What you lose is the newest material: anything added since that date is not in its answers yet. Try the rebuild again starts a fresh one, and the notice clears itself when that finishes.
If it keeps failing, the source added just before it is the usual cause — remove it, rebuild, and add it back on its own to see.
Sources and citations
A grounded answer cites the passage it used, and a visitor can open it and read the surrounding text. hiy's own summary of your material is never quoted to a visitor and doesn't count as one of your sources — only what you actually wrote does.
You choose whether visitors see the sources behind answers at all. Hiding them hides the citations from visitors — your own test chat still shows you everything. What no setting hides is an honest gap: when your twin says it doesn't know, it still shows how many searches it ran first.
When your sources don't cover something
The twin says so rather than guessing, and shows how many searches it ran first. That question then queues for you, and answering it once turns your answer into a source the twin cites from then on.
Removing a source takes it out of the next rebuild. Correcting one is authoritative — it overrides the outdated claim outright. Either way, fix it once and the old claim is gone.