Is it safe to let it use my browser?

You watch every step as it happens, and you can stop it at any moment with one click. The instant you use the page yourself, it pauses and waits for you.

Do I need to know anything technical?

No. You describe what you want in plain words — “fill this form”, “compare these three pages” — and it figures out the rest.

What does the free plan include?

Bronze gives you the browser sidekick itself — the agent on your current tab, web search, projects, chats, notes and sync between the extension and the web app — running on the Standard AI, with one usage allowance per 5-hour window. No card required. Four things are not in Bronze: the Smarter AI, downloadable file deliverables, Guidelines, and Libraries. Those start at Silver.

Can it read scanned documents and images? (OCR)

On Gold and Diamond, yes — those plans run OCR, so scanned PDFs, photographs of pages and plain images are read as well as ordinary files. Slide decks never needed OCR: a .pptx is read as text on every library plan. Silver is text extraction only and refuses a file with no text layer rather than adding an empty document.

What if I hit the usage limit?

You wait for the reset. The window is fixed, not rolling: it starts the moment you first use the Standard AI and runs for five hours, and the whole allowance comes back at once when it ends. Paid plans multiply the size of the allowance rather than shortening the window.

How do golden credits actually work?

Golden credits are the currency for the Smarter AI, and they are not one-per-reply — a credit tracks the work in the reply. Plan credits arrive monthly with a small daily top-up and roll over up to two months' worth. Credits bought in a pack sit on top, do not expire and are spent only after plan credits run out.

Do the pricier plans answer faster?

On the Standard AI, no — every plan is answered by the same self-hosted model and there is no fast lane. On the Smarter AI, Gold and Diamond send their requests to the provider flagged priority while Silver sends them as standard. Gold and Diamond share that same queue.

Can I use it away from my browser?

Yes — the web app has all your same conversations and screenshots, readable from anywhere. Actions on live pages happen in the browser, and it will point you there when needed.

Searching Your Own Documents

Q: What is a Library?

It is your own documents, kept where your AI can read them. Upload contracts, specs, research, spreadsheets or notes; StickyFriend reads each file, indexes it, and from then on any chat you point at that library can search it and quote from it, telling you which file the answer came from. Silver gets 3 libraries, Gold 15, Diamond 50; Bronze has no access.

July 31, 2026

An attachment and a library are not the same tool

Attaching a document to a conversation solves exactly one question, in exactly one chat, and then the document is gone again. That is fine for a one-off. It is useless for the thing people actually want, which is: this body of material is the ground truth for my work, and I want to be able to ask it anything, from any conversation, for months.

A library is that. You upload contracts, specs, research, spreadsheets or notes once; StickyFriend reads each file and indexes it; and from then on any chat you point at that library can search it and quote from it.

What happens when you upload

A file goes through three visible stages, and the visibility is the point:

Read. The text is extracted from the file. You watch each file’s status while this happens rather than staring at a spinner over the whole batch.
Indexed. The content becomes searchable. Until this finishes, a chat pointed at the library will not find it.
Failed, with a reason. If a file cannot be read, it is marked Failed and the reason is on screen, along with what would fix it. It is not quietly added as an empty document — which is the failure mode that matters, because an empty document does not error, it just makes the library confidently incomplete.

Answers name the file

When an answer comes out of your library, it tells you which file it came from. This is not decoration. A quote you can trace is a quote you can check against the original clause, the original spec, the original number — and checking is the entire reason you put your own documents in front of an AI rather than trusting its general knowledge.

Try this on day one

Ask your new library a question you already know the answer to, and look at which file it cites. Two minutes of that tells you more about whether the upload really worked than any progress bar.

Which chats can read it — the default is none

Each conversation picks which libraries it may read. The library button sits beside the Smarter toggle, above the message box, and shows the count on its face, so you can always see whether the chat you are in is reading your documents.

A chat with none selected reads nothing of yours and costs nothing extra, and that is the default. Pointing a chat at a library is a deliberate act, not something that happens because you once uploaded a file.

What gets read without OCR, and what needs it

This is the part that is usually explained badly, so plainly:

Text extraction covers more than people expect, and it is on every plan that has libraries at all: PDFs with a text layer, Word, Excel, CSV, HTML and plain text.
Slide decks do not need OCR and never did. A .pptx or .ppt is read as text on every library plan — slide text, table cells and speaker notes, one slide at a time. OCR is only called for an individual slide that turns out to be a picture with no text on it. If you have presentations to put in a library, Silver reads them.
OCR is for scans and photographs. Scanned PDFs, photographs of pages and plain images need a model to look at the image. That runs on Gold and Diamond.
Silver is text extraction only, and says so before you upload. A file with no readable text layer is refused, or marked Failed with the reason and the upgrade named.

OCR sits on the bigger plans because it is the most expensive step in the pipeline — a model call per page or per image — not because of an arbitrary tier line.

What each plan allows

Bronze — no libraries at all. Libraries are a paid feature, and the block is enforced on the server rather than hidden in the interface.
Silver — 3 libraries, 200 files, 2 GB. Text extraction only.
Gold — 15 libraries, 2,000 files, 20 GB, with OCR.
Diamond — 50 libraries, 10,000 files, 50 GB, with OCR.

Libraries, files and storage are metered against your plan on the Libraries screen and in the extension, with a warning before you reach the ceiling instead of a refusal after it.

How to organise them so they stay useful

One library per body of knowledge, not per file. “Supplier contracts” is a library. “Contract with the supplier” is a file. Three libraries goes a long way when they are drawn along real boundaries.
Use folders inside a library for the structure you already think in — by year, by client, by version.
Keep the noisy stuff out. A library that contains eleven drafts of the same document will cite you a draft. Upload the version you would actually act on.
Point a chat at the narrowest library that can answer it. It is faster to read and much easier to sanity-check the citation.

The honest limits

Libraries do not make the AI infallible, and they do not read a document you did not upload. A citation tells you which file an answer came from; it is still worth opening that file when the answer is going to cost you money. And on Silver, a folder of scanned PDFs is going to tell you it cannot read them — deliberately, and before you have built a workflow on top of a library full of blanks.

The full plan detail is on the pricing section, and the FAQ answers the OCR question in one paragraph if you want it even shorter.