Keeping your library up to date

Updating an uploaded file

There's no in-place edit for a static file: what you uploaded is what's indexed. Updating one is a quick replace.

1. Delete the old source

   On the Knowledge page's Sources sub-tab, expand the library, find the outdated source and delete it.

   Note

   If that source is also used in other libraries, deleting it offers two choices. Remove from this library takes it out here while it stays available in the others — the right pick when you only want to refresh this library. Delete sends it to the Recycle Bin and removes it from every library at once (restorable). A non-shared source just deletes to the Recycle Bin.

2. Upload the new version

   Add the new file the same way you originally added it. It becomes a fresh source and starts processing.

   Note

   The new version doesn't get a row straight away: while it processes, its name shows in a strip above the library's list — Queued, then Processing — and it appears in the list as its own row once it's processed. The strip comes back if you reload the page. If the upload fails, its line shows Failed (hover it for the reason) and, when the file can be retried, a Retry button that opens the file picker so you can upload it again; Activity has the full job.

3. Wait for it to finish processing

   The new version is processed once it appears in the library's list as its own row; a single file never gets a status label. The Activity sub-tab tracks its progress (hit Refresh to update the feed). From its next reply onwards, the Clone retrieves from the new version.

Keeping website sources fresh

A website source is a snapshot, not a live mirror. The crawl captures the site at that moment, and your Clone reads from the captured copy — update the live site five minutes later and the Clone won't notice. You have three ways to bring a snapshot up to date:

• Scheduled re-sync — on the Synchronization sub-tab, switch on the site's own Auto-sync and the platform re-fetches it automatically, at the cadence you pick. A website's Auto-sync stays off until you switch it on. The next section walks through it.
• Manual re-sync — click the circular-arrow Synchronize button on the website's row in Sources when you've just published a change you want reflected straight away. Its options are explained just below.
• Replace the source — delete the website source and re-add it. A fresh crawl from scratch is sometimes cleaner when the site's structure has changed significantly.

While a re-sync crawls, the source row shows a live status such as Syncing: 22 found, 140 reviewed — the reviewed count keeps climbing even when found plateaus, so a rising reviewed number means the sync is still working.

For a website, Synchronize opens the Sync window. Pick one of its three options and click Start Sync: the sync runs in the background, and the bell tells you when it's done. The window opens on New + Changed every time:

Take a source out of use without deleting it

Sometimes a source should sit out for a while — last season's price list, or a page you're rewriting. Exclude it instead of deleting it: every source row in Sources, apart from the empty-media rows described below, has a slashed-circle button, Exclude from the clone's knowledge.

• Click it and a toast confirms: Source excluded — the clone will stop using it in a few seconds. The row stays in the list, greyed out, and nothing is deleted.
• An excluded source is out for every library that uses it, not just this one.
• Syncs leave an excluded source alone: they don't update it, even when the page has changed, and they don't move it to the Recycle Bin.
• To bring it back, click the same button — now a tick in a circle, Include in the clone's knowledge again. The toast reads Source included — its content is being re-added to the clone's knowledge.

Some rows are excluded for you. When a website or YouTube collection picks up a video or audio clip that comes out empty, IcloneU keeps it as an excluded row, so later syncs don't download and transcribe it again. A short tag after its name says why — No speech found, Couldn't transcribe, Not available on the platform or Longer than the allowed duration — and hovering the tag adds "Nothing from it reaches the clone. Use Retry to process it again." These empty-media rows have a circular-arrow button, Retry: process this media again, in place of the slashed circle, because including an empty row would add nothing. Retry processes that one item again, which uses units; if it still comes out empty, it stays excluded with its reason. Syncs never retry it on their own.

Next to a source's title, an information icon holds the summary IcloneU keeps for it: hover for a preview, click to open it in full. A source without a summary usually shows a circular arrow instead, Summary not generated yet — click to generate. Click it and IcloneU writes one (Summary generated.). When IcloneU no longer keeps its own copy of the source's content but still has the copy your Clones search (the indexed copy), it writes the summary from that copy and changes nothing else, with a different message: Summary generated from the indexed copy of this source, which may be out of date. Sync the source to rebuild it from the original. With no copy left at all, you'll see Can't regenerate this summary: the original content is no longer available.

Scheduling automatic syncs

The Synchronization sub-tab on the Knowledge page controls re-fetching for every syncable collection in your account. It has two halves: Global defaults on top, Per-collection overrides below.

1. Open the Synchronization sub-tab

   From the left sidebar, open Knowledge and switch from Sources to Synchronization.

2. Switch on auto-sync

   Enable the Auto-sync enabled master toggle. While it's off, no collection syncs on a schedule, whatever its own setting; Synchronize and Sync now still work. While it's on, a collection syncs on a schedule once its own Auto-sync is on under Per-collection overrides. Switching a collection's Auto-sync on, or adding a Shopify (pages & blogs) collection, turns the master toggle on for the whole account, so every other collection that is switched on syncs on schedule again.

3. Pick a default cadence

   Set how often syncable collections re-fetch — every N day(s), week(s) or month(s). This default applies to every collection that doesn't override it. Click Save to apply the master toggle, the cadence and the Limits covered below; the switches under Per-collection overrides save as soon as you flip them.

4. Override per collection where needed

   Each row in Per-collection overrides has its own Auto-sync toggle and a Cadence that reads INHERITED until you set a custom value with the edit pencil, plus Last sync and Next sync timestamps. Next to INHERITED, the Cadence column shows the default cadence from the step above, which is what the collection syncs at; save a new default and the Next sync of those collections moves to match it, counting from their last automatic sync. Most collections start with Auto-sync off and a dash under Next sync until you switch them on; Shopify (pages & blogs) collections start switched on. While the master toggle is off, a collection that's switched on still shows its Next sync, but nothing runs until you switch the master back on. A local folder's row shows Uploaded files — upload them again to update instead: its files are on your computer, so it can't sync from here.

   Tip

   To pause a single collection without touching the rest, switch its Auto-sync off.

Global defaults also include Limits — cost guards that stop an automatic sync from running up your bill. Anything that exceeds them is skipped and surfaced in the Activity log, so you can see what was filtered out:

A video or audio clip on a website that runs past the video or audio limit also shows in that website's collection as an excluded row tagged Longer than the allowed duration. To take it in, raise the limit, click Save, then use the row's Retry: process this media again button. A video over 180 minutes stays excluded whatever the limit.

Confirming changes in Activity

The Activity sub-tab is the audit trail — "Background jobs across all your libraries — uploads, crawls, syncs, retries", as the page itself puts it. Each row is one processing event, with Collection, Phase, Status and When columns; the Phase column reads Discovery, Upload to AI or Sync (the Type filter calls Upload to AI jobs Loading).

Two buttons round it out: Refresh reloads the feed while you wait on an in-progress job, and Open details drawer gives a closer view of a selected entry. Items skipped by the sync limits also surface here, so a quieter-than-expected sync run has an explanation. On a New + Changed sync, pages that haven't changed count as skipped too, so a large skipped number is normal.

Frequently asked