Your paper trail, digitized and searchable. Never rummage through a drawer looking for a warranty again.
#What It Does
Documents in ambientChat are digital copies of the real-world paperwork that accumulates around your life — receipts, product manuals, warranties, certificates, contracts, and anything else worth keeping. When you upload a document, the AI reads it, extracts the important details, generates a summary, and tags it for easy searching later.
The magic is in the connections. A receipt doesn't just sit in a folder — it links to the inventory items it created. A warranty knows which product it belongs to. Your AI assistant can search across all your documents when you ask about purchases, coverage, or that thing you bought six months ago whose name you can't remember.
You can upload files you already have, not just photos: PDFs, Office files — Word (.docx), Excel (.xlsx), PowerPoint (.pptx) — and spreadsheets exported as CSV or TSV (.csv, .tsv). The text inside them is extracted so they're fully searchable and available to your AI assistant, exactly like the documents you can ask the AI to create for you (see Creating Documents). Uploading and generating produce the same kind of searchable document.
Turn a spreadsheet into inventory. Open any spreadsheet — Excel .xlsx, .csv or .tsv — and choose Create items from this… from the ⋯ menu. Chat opens with the request ready; the assistant shows you which column it will use for the name, brand, category and so on, and once you agree it imports every row in one step, however long the sheet. Extra columns such as a year or a record label can be kept together in each item's notes. Say "undo that" to remove the whole import.
A CSV gets a little extra: the app reads the table, so opening one shows its columns and first rows as a proper table — you can see what's in a spreadsheet without downloading it — and tells you how many rows and columns it holds. Your AI assistant can answer questions about the contents. Very large CSVs are still stored whole and downloadable, but only the first portion is read into a conversation; the app says so rather than quietly answering from part of the file.
Text files you can edit. Notes (.md), plain text (.txt), and spreadsheets (.csv, .tsv) all open on the same editing screen. You read them the way they're meant to be read — a note renders as formatted text, a spreadsheet renders as a table — and the pencil switches to editing the file itself. See Editing a Document below.
#Document Types
The system recognizes and handles several document types, each with tailored AI extraction:
| Type | What It Is | What AI Extracts |
|---|---|---|
| Receipt | Proof of purchase | Store name, items, prices, date, payment method, tax, subtotal, total |
| Manual | Product documentation | Product name, key instructions, specifications |
| Warranty | Coverage information | Product, coverage period, terms, provider |
| Certificate | Certifications, diplomas | Issuer, date, subject, validity |
| Contract | Agreements, terms of service | Parties, dates, key terms, obligations |
| Scan | General scanned documents | Text content, summary |
| Help Guide | Built-in guides (like this one) | Title, content, tags |
| Note | Your own written documents | Content, summary |
A scanned receipt is titled after its store (for example "Receipt - Costco"). That title is its name everywhere, on the phone and on the web, so you can rename a receipt like any other document (long-press it on iOS, or use ••• on the web). A receipt with no title falls back to showing its store.
#How to Use It
#iOS App
Uploading a document:
- Open the Context tab, then Docs
- Tap the Upload button (plus icon)
- Choose your source:
- Camera — take a photo of a receipt, document, or label
- Photo Library — select an existing image
- File Browser — pick a PDF, an Office file (Word
.docx, Excel.xlsx, PowerPoint.pptx), a.csv/.tsvspreadsheet, or an image from your device
- The AI processes the document automatically — extracting text, generating a summary, and assigning tags
- Your document appears in the current folder, ready to view
Viewing a document:
- Tap any document to open it
- Images display with pinch-to-zoom
- PDFs open in a built-in viewer
- Markdown files render with full formatting
- The document detail screen shows the AI summary, extracted data, tags, and any linked inventory items
Linked items:
When a receipt or product scan creates inventory items, those items are linked back to the source document. You'll see a Linked Items section on the document detail screen. Tap any linked item to jump straight to it in your inventory. On the web this section is there however you opened the document — from the Docs tab or from a chat answer — and clicking an item opens it on top of the document. Documents someone has shared with you don't list their linked items. The list is the same on iPhone, on the web and for an AI you've connected: it includes everything a receipt's lines point at, even when the item itself doesn't point back, and each price is shown in its own currency. It works both ways: an item's Documents section lists the receipt it came from (and any document that lists it), and unlinking an item from a receipt takes it off both.
#Browsing a big folder (iOS and Web)
A folder arrives a screen at a time. Sorted by Name, Added or Modified, the app fetches the first hundred documents in that order and loads the next hundred as you scroll — so a folder with thousands of documents opens as quickly as one with ten, and scrolling still reaches the end. The order is the whole folder's order, not the order of whatever happened to load first: the second page continues exactly where the first stopped.
One consequence of that, the same on iOS and the web: under Name, titles beginning with a capital letter come before titles beginning with a lowercase one — "Warranty" sorts ahead of "acme receipt". The sorting is done where the documents are stored, and that is the order it uses. Nothing is missing; look further down the list.
The format row pages too. Narrow a folder to Images, PDFs, CSV, TSV, Office, Notes or Web pages and the library itself does the narrowing: the first screen is full of that kind of file, even in a folder that is mostly something else. A folder of a hundred PDFs with three photos at the bottom shows the three photos straight away under Images — it used to show an empty grid until you scrolled. Every way a kind of file is stored counts: a scanned photo and a .png are both Images, and a note uploaded as .md is a Note.
The counts on those chips describe the folder, not the part of it you have scrolled: "PDFs 40" means forty in this folder. (iOS prints the numbers; the web offers the same chips without them.) And on both, a format is offered even when none of its documents have loaded yet — otherwise the chip you need would be the one missing.
The other sorts — My order, Type, File size — still read the folder in one go, because they arrange documents in ways only your phone can. Those are the ones to be wary of in a very large folder. Offline, every sort and filter reads what is already on the device.
If a page can't be fetched, the foot of the list says so and offers Try again rather than stopping quietly.
#Finding something you just added — Recent (iOS and Web)
Tap Recent at the front of the chip row and the list becomes every document you have, in every folder and Home, newest first. Each one says which folder it's in — or Home — so it answers "where did I put that?" without opening a single folder. Scroll and it keeps going, all the way back. While Recent is on, folders and shared documents step aside and the format chips hide, because Recent means everything; tap Recent again, or pick a sort, to go back to the folder you were in. Your saved sort isn't changed. Recent replaces the old Just Added chip, which only looked inside the folder you already had open.
#Searching (iOS and Web)
Tap the search button (iOS) or open the search bar (Web) and type. Search covers every document you own, in every folder — you never have to open a folder to search inside it. It matches on the title, the AI summary and tags, the document type, the file name of an uploaded file, the store on a receipt, and the beginning of the document's own text — so the serial number on the first page of a manual, or a line on a receipt, is found even when the title says nothing about it.
While the search runs you'll see a spinner, then a count under the box: "9 matches" means exactly nine; "9+ matches — scroll for more" means more are still loading as you scroll. Offline, the phone can only search the documents already on it, and the count says so. A search matches parts of words too ("yson" finds "Dyson") and ignores accents.
How deep it reads. The exact matches index the first ~2,000 characters of a document's text — enough for a receipt, a letter, or the front page of a manual. A phrase deep inside a long PDF is not among the exact matches; you can still ask your AI assistant ("find the page in my Dyson manual about filter cleaning").
More by meaning. Beneath the exact matches you'll see a second section, More by meaning: documents the AI thinks are about what you typed even though the words don't appear — a photo filed as a scan when you searched "pic", a "vacuum cleaner guide" when you searched "hoover". It reads the whole document, not just the first page. These are kept separate from the count above ("9 matches · 4 more by meaning") so you always know which results are exact and which are the AI's suggestion.
#Finding a word inside a document (iOS and Web)
Open the document, tap ⋯, then Find in document — or press ⌘F (Ctrl-F) on the web. A search bar appears at the top. Type, and every match is highlighted as you go, with the current one in a stronger colour and a count beside the box: "3 of 12". The ↑ ↓ buttons step backwards and forwards and bring each match into view (on the web, Enter and Shift-Enter do the same; on the phone, the keyboard's Search key moves to the next one). ✕ closes the bar and clears the highlights.
It ignores capitals and accents and matches parts of words — "towel" finds "Paper Towels", "cafe" finds "Café" — and it treats the iPhone's curly apostrophe the same as a straight one, so "Steve's" is found however it was typed.
It searches the document's own words: a note, a checklist (ticked items included), a text file, or the text read out of a Word file. For a PDF or a scanned page it searches the text the app read from it and opens the Distilled text section so you can see each match. It can't highlight the words on the page picture itself.
On a checklist — "is it already on the list?" — if nothing matches and you can edit the list, the bar offers Add "paper towels" to the list, one tap.
On a spreadsheet (CSV, TSV or Excel) find searches every row of the file — not just the rows the preview shows — and every sheet of an Excel workbook. The table switches to the rows that match, with the matches highlighted, and the count is the whole file's: "1 of 312" means 312 matches across all the rows. Long answers show 200 rows at a time; Show more (or stepping past the last one with ↓) brings the next. Find isn't offered on a spreadsheet someone else shared with you yet.
Find works while you're reading a document, not while you're editing it.
#Web
- Go to the Documents section
- Click the Upload button
- Select one or more files — images, PDFs, Office files (Word
.docx, Excel.xlsx, PowerPoint.pptx),.csv/.tsvspreadsheets, and.mdmarkdown files are all supported - Documents are processed and appear in the current folder
- Use drag-and-drop to move documents between folders — just drag a document card onto a folder
Adding an image to Documents files it — it does not become inventory. Drop a photo into a Documents folder and you get one document, with its type, the date you added it, and the folder it went into. The AI still reads it, so it is searchable and you can ask about it — but it will not be broken up into inventory items. A photo of your lounge stays a photo of your lounge; if you want the things in it catalogued, use Scan. (The same goes for a receipt: dropped into Documents it becomes a receipt document you can search, not a shopping list of items.)
Or skip the button entirely — drag files straight in from your desktop. Where you drop decides where the file lands:
| Drop it on… | It uploads to… |
|---|---|
| Anywhere in the documents area | The folder you're currently looking at |
| A folder card | That folder — you don't have to open it first |
| A folder name in the breadcrumb trail | That folder, however far back up you are |
Drop several files at once and they upload together. If any of them can't be used, you get one message at the end saying which and why — the rest still upload.
#Via Chat
Your AI assistant can search and retrieve documents on your behalf. Try:
- "Show me my receipts from Costco."
- "Find my laptop warranty."
- "What did I buy at Target last month?"
- "Do I have a manual for my air fryer?"
- "How much did I spend on groceries this week?"
You can also attach files directly in chat. Tap the attachment button, select a file, and choose which folder to save it to. The AI will process the document and include its contents in the conversation.
#Via Claude Desktop (MCP)
If you've connected ambientChat to Claude Desktop via MCP, you can access your documents with these tools:
list_documents— List documents, optionally filtered byformat(image,pdf,csv,tsv,office,markdownorlink— every stored spelling of that kind of file), type, category, and folder. Each document reports itsformat, andinclude_facetscounts them per format. Passsearchfor an exhaustive text filter across every folder (title, summary, tags, file name, store, start of the text) — paged, with an exact countget_document— Get full details — AI summary, linked items, metadatasearch_documents— Keyword search across titles, summaries, and contentsearch_documents_semantic— AI-powered semantic search by meaningupdate_document— Update a document's title, description, tags or type (not into a help guide, web page, bio or exhibit — those refuse withTYPE_NOT_ASSIGNABLE)update_text_document— Replace the contents of a note,.txt,.csvor.tsv. Send the whole new text, not a patch, with thesource_hashyou read — if someone saved in between, the save is refused rather than overwriting their edit. Refuses a spreadsheet that doesn't parse rather than saving a broken fileundo_text_update/redo_text_update— Step a text document back or forward through its edit history. For a spreadsheet this restores the previous file, exactlylist_document_versions/get_document_version— See a note's saved versions (V number, date, who saved it and via which AI app) and read any one of them. Kept for 90 days, and never fewer than the last 50 savessave_document_version_as_copy— Save an earlier version as its own editable document ("Costco Shopping List - V8"), without changing the originalread_document_rows— Page through a stored spreadsheet's rows without loading the whole fileupload_document— Upload a new document for AI processingmove_document— Move a document between folderstrash_document/restore_document— Soft delete and restoreregenerate_document_image— Generate a new AI illustration thumbnail
For the full tool reference, see MCP Tools — Complete Reference.
Example: Ask Claude Desktop "Search my ambientChat documents for appliance warranties" and it will use these tools to find and display them.
#Multi-Page Documents
A manual, warranty booklet, or contract is one document with many pages — not a pile of unrelated photos. Open any photo document and you'll see a PAGES strip:
- Add pages — photograph the rest and add the shots. They become numbered pages of that one document, in the order you add them. Works on iOS (Take Photo / Choose from Library, multi-select) and in the web interface.
- Tap a page to read it — it opens in the big preview above the strip, and the strip marks where you are. Tap the big preview to open that page full size, where you can zoom and swipe through the rest. The ✕ removes a bad shot and the rest renumber.
- Ask about a page — "read page 11 of the drill manual". The AI can look at whichever pages you name, which matters for a long manual: without naming them it only ever sees the first few.
- In chat — attach the photos and say "add these as pages of the drill manual".
The document's original photo stays as page 1, and a document always keeps at least one page — trash the whole document instead of emptying it.
A document someone shared with you keeps its owner's pages. You can read every page, but Add pages and the ✕ are the owner's alone. Can edit access lets you change everything else the owner can — the title, description, notes, tags, type and a text document's words — and remove its picture or give it a new one from your own library (⋯ → Use an existing image…). The picture you choose is copied into the owner's copy, so it stays even if you later delete your original. You can't Iconify it, move it to another folder or change who it's shared with. You change them with the same controls the owner uses (see Changing a Document's Type and Tags and Changing a Document's Picture below). Same on iOS, the web, and in chat.
Already uploaded a manual as separate photos? Turn on Select, tick the pages in the order you want them, and tap Combine. They become one multi-page document: the first one you selected keeps its title and stays where it is, the rest become its pages and go to Trash — so if you pick the wrong ones, nothing is lost. Any item they were attached to stays attached. Combine only appears for photo documents.
PDFs already paginate themselves, so they don't take photo pages — their pages are rendered from the file, and you read them the same way: tap a page to bring it into the big preview, or use the arrows at the sides.
The arrows turn pages first. Only when you reach the last page does the next arrow move on to the next document in the folder — and going back from page 1 takes you to the end of the previous document, so paging back and forward returns you exactly where you were. Photo pages can be added and removed; a PDF's are rendered from the file, so they are read-only.
A PDF's previews appear a minute or so after you upload it. If you open it before then, the preview fills in by itself once page 1 is ready — no need to close and reopen.
Only the first 20 pages of a very long PDF get previews — the strip says so ("20 of 60") and the arrows stop there rather than pretending. The AI still reads the whole document's text either way, so "read page 44" works even when page 44 has no preview.
#Deleting a Document
Deletes are soft — documents go to Trash and stay recoverable for 30 days.
In Thumbnails view every card has a trash can — in its top-right corner on iOS, and on the web in the row of small round buttons at the tile's bottom-right, beside move to a folder and ••• (Share, Rename). One tap sends it to Trash, with no confirmation dialog: the card disappears immediately and Undo waits in the Snackbar, which is a better answer to a mis-tap than a prompt you'd learn to click through. The control is hidden in selection mode, where the checkbox owns that corner, and it never appears on a document someone shared with you — deleting stays with the owner.
You can also swipe a row, use ⋯ → Delete from the document itself, or select several and delete them together. Whichever you use, you come back to the list where you left off rather than at the top.
#File Size
Every document knows how big it is, and says so:
- In the document's details — a Size row, next to its format and dates. On iOS, in the web interface, and on the page for a note or spreadsheet.
- In your folders, in every view — in List and Text list it sits on the end of each row's meta line, after the format and the date. In Thumbnails it has a line of its own under the date, so it never gets cut off on a narrow card. Same on iOS and the web. A document someone else shared with you — directly, filed into one of your folders, or inside a folder they shared — shows its format, date and size the same way, with Can view or Can edit on the end of the row's line and who shared it beside it; on a thumbnail the access sits under the title and the size on its own line beneath it.
- A line of what it's about — in List view each document shows its one-line summary under the format, date and size (for a receipt with no summary, the store), on iOS and the web alike — your own documents and ones shared with you or filed into your folders — so two receipts with the same name can be told apart.
- Which date it is — every document in a folder, receipts included, shows when it was last Updated, in every view and on iOS and the web alike. Open a document and its details show both dates: Added (when it arrived) and Updated (the one the folder shows), each with its time — so a document added and edited on the same day shows two different times — on iOS and the web. The date printed on a receipt is in its details too.
- As a sort — pick File size from the sort control to find the heavy things. Largest first by default; tap again for smallest first.
What the number means is "the file you'd get if you downloaded it". A photographed multi-page document counts all its pages, because each page is part of the document. A PDF counts the PDF, not the page previews we render from it. A note or a spreadsheet you typed counts its text. Edit a note and its size follows the edit — it is measured from what the note says now, not from when you created it.
A document with no size shown is one we couldn't measure — its file lives somewhere outside your library, or it has gone missing. Those sort to the bottom either way, so they never masquerade as the smallest thing you own.
Sizes appear on everything created from now on. Documents you already had get theirs when the one-off backfill runs — until then a few older ones may show no size and sort to the bottom.
#What an Upload Costs
Uploading a Word, Excel or PowerPoint file, a spreadsheet (.csv / .tsv) or a plain-text note costs a few credits. The file itself is read for free; the credits pay for the AI that gives it a proper title, a short summary and tags, so it reads like something you'd recognise rather than a bare filename. If that step fails — or you're out of credits — the document still arrives, searchable, under its filename, and you aren't charged.
You're charged once per upload, even if a hiccup makes it try again.
#Tips & Tricks
- 👍 or 👎 a document. Thumbs up or down sit at the top of every document, on iOS and the web — a recipe you'd cook again, an article worth keeping. Tap the filled one to clear it. In a list, every document's tile and row has the same one-tap 👍 | 👎 pill beside its other buttons, on iOS and the web; swiping a row on iOS, long-pressing it, or the web's ⋯ works too. The web list also stopped printing Documents both above and below the Favourites. Liked documents lead their folder under Favourites, newest like first; the rest keep their order. A 👍 isn't an edit: the document keeps its place under Modified and its "Updated" date, for you and for anyone you've shared it with. My order keeps your own arrangement, with no Favourites above it, and a search keeps its own order.
- Sort by file size to find what's eating your allowance. A handful of multi-megabyte scans usually outweigh hundreds of notes. Largest-first in a folder shows you which they are.
- Scan receipts sooner rather than later. Thermal paper receipts fade over time, and once they're too faint, even AI can't read them. Snap a photo while the ink is still fresh and you'll have a permanent, searchable record.
- The AI summary is often enough. You don't always need to open the full document. The summary on the document card captures the key details — store, total, date — so you can find what you need at a glance.
- Print on the web goes straight to your print dialog. Choose ⋯ → Print on a document (or Print on an item, an answer, or a selection) and a "Preparing to print…" note appears for a moment, then your browser's print dialog opens on the printable page — its preview is what will print, and Save as PDF is in the same dialog. A document that is itself an uploaded PDF prints as that PDF, straight to the same dialog. (In Safari, and for a very large PDF, press Open PDF on the note and print from the PDF — Safari can't print a PDF without showing it first.)
- Use folders to stay organized. A few well-named folders (Warranties, Medical, Home) go a long way — receipts file themselves (see The Receipts Folder below). See the Folders guide for more on organization.
#The Receipts Folder (iOS and Web)
A receipt you scan no longer lands loose in My Documents. The app makes a Receipts folder in Documents and files every scanned receipt there. If you already had a top-level Documents folder called "Receipts", that one is used.
File receipts like their items (on by default). Inside Receipts, the app makes folders that match where the receipt's items are in Inventory. Scan a shoe receipt whose sandals are filed under Closet › Shoes, and the receipt is filed under Receipts › Closet › Shoes. When you — or your AI assistant, or an AI app you've connected — move those items to another folder, the receipt moves with them.
- Items in different folders. A document can be in one folder, but an item can be in several. When a receipt's items are in different places, it goes in the deepest folder they all share (both pairs of shoes in Closet → Receipts › Closet), or the top of Receipts when they share none.
- You always win. Move a receipt yourself and it stays where you put it; it stops following its items. A receipt you filed in a folder before this existed also stays put.
- No clutter. A matching folder the app made is removed once its last receipt leaves. Folders you made yourself are never removed.
- Every kind of move counts. Undoing a move, restoring items from Trash, or deleting an Inventory folder whose items also live elsewhere all bring the receipt along; rename or move an Inventory folder and its matching folder under Receipts is renamed or moved too.
- Already in My Documents? Scanned receipts still at the top level of My Documents, and linked to items, move into Receipts once. A receipt file you uploaded there yourself stays.
- A scan you start inside a Documents folder still files the receipt in that folder — you chose it.
- A receipt you attach from an item's page stays with that item, as before; it isn't filed in Receipts.
Hide the Receipts folder (off by default). Turn it on and the Receipts folder stops appearing when you browse Documents, or in the folder lists for moving things. Your receipts aren't gone: they still open from the item they belong to, search still finds them, and you can still ask your AI assistant about them.
Both switches are together under Control → App Behavior → Receipts, each with its own icon, on the phone and on the web. You can also just ask: "Stop moving my receipts" or "Hide the Receipts folder." Moving receipts is folder housekeeping only — it costs no AI credits.
#Options
| Setting | What It Does | Default |
|---|---|---|
| Auto-tag | AI automatically assigns tags to uploaded documents | On |
| Default folder | Where new documents are saved when no folder is selected | My Documents |
| File receipts like their items | Scanned receipts go in Receipts, in folders that match their items' Inventory folders, and move when the items move | On |
| Hide the Receipts folder | Leaves Receipts out of browsing Documents; receipts still open from items, search and chat | Off |
#Where Is This Document Filed? (iOS and Web)
Under the title of every document of yours, in small grey text, is the folder it lives in — on the phone and on the web, while you read it and while you edit it:
🏠 › Meeting Notes › Founders Move…
- The house is Home (My Documents). If the document isn't in any folder, the line says 🏠 My Documents.
- Tap or click any folder in the path to open it in Docs and see what else is there. The house takes you to the top.
- Deep folders are shortened to the last two, with … in front — tap … to see the whole path. On the web, hover over the path to see all of it; on the phone, press and hold.
- Move… opens the folder picker so you can file it somewhere else. The path updates as soon as it moves.
- While you're editing, the path still shows where the document is, but tapping it doesn't take you away from your edit, and Move waits until you press Done.
- A document someone shared with you doesn't show the line yet — the Shared by banner says whose it is, and Filed in under its file details says where you filed it. Never the other person's folders.
- Asking your assistant "where is my founders meeting note?" gets the same whole path the screen shows.
#Editing a Document
Notes, plain text files and spreadsheets can be edited in place — you don't have to download, change, and re-upload.
How it works
- Open the document. A note shows as formatted text; a
.csvor.tsvshows as a table. - Press the pencil (top right).
- Edit, then press Save. Cancel throws the edit away.
What you're editing, for a spreadsheet
You edit the file's real text — one row per line, values separated by commas (or tabs, for a .tsv). That's deliberate: it's the actual file, so nothing is lost in translation. Two things worth knowing:
- A value containing a comma or a line break must be wrapped in double quotes —
"Smith, John"is one value,Smith, Johnis two. The editor tells you if you leave a quote unclosed, and refuses to save rather than saving a broken file. - One row can span more than one line when a value contains a line break. So a 95-row spreadsheet may show more than 95 numbered lines. The count above the editor always tells you the real row and column totals.
Changed your mind? Ask your assistant to "undo that edit". For a spreadsheet this puts the previous file back exactly as it was — not an approximation of it. You can undo repeatedly, and redo if you undo too far.
When editing isn't offered
Very large files are read-only in the app, and the screen says so with the actual number — "This has 12,480 rows — too many to edit in the app. Download it to change it in a spreadsheet app." There's no greyed-out button to puzzle over: either the pencil is there, or there's a sentence explaining why it isn't. Other reasons you might see: the file is bigger than the app can safely edit, someone else is editing it right now, or its stored file is missing.
Everything else — PDFs, images, Office files (.docx/.xlsx/.pptx) — is not editable in the app. Download those, change them in the app that made them, and upload again. A .xlsx in particular can hold several sheets, and the editor is built around single-table files.
#Going Back to an Earlier Version (iOS and Web)
Every time a note is saved, ambientChat keeps the version before it — every save from the last 90 days, and never fewer than your last 50.
- Open the note and tap the purple V8 tag (it shows the note's current version number; a spreadsheet or text file says History).
- Versions lists every saved version, newest first: its number and who saved it, in the same words an item's Recent changes uses — "You", "You, via chat" for a change you asked the chat for, "Grok, for you" for one your own AI app made, and "Shared with you: Kathy, via ChatGPT" (or "…, via chat") for someone you share with. On a shared list, the bar says it as a sentence: "Kathy via ChatGPT added “Oat milk”", "Grok added “Oat milk” for you", "Chat added “Oat milk” for you". The one you're looking at is marked Current.
- Tap a version to preview its text.
- Tap Save as new document to get it back as its own editable note — "Costco Shopping List - V7", in the same folder. The note you started from is not changed.
To roll the note itself back instead, use Undo in the ⋯ menu. You can also ask your AI: "What did my Costco list say yesterday?" or "Save V7 of my packing list as its own note."
A note someone shared with you has the same tag. Tap it to see the owner's saved versions — so if an AI rewrote the household list and your line vanished, you can find the version that still had it. Save as new document puts the copy in your documents, not the owner's. A line someone else has marked Just me is left out of the versions you see too, including ones saved before it was made private — and it stays out even after they reword or delete it. Undo on an old version never brings it back for everyone either.
#Changing a Document's Picture
Every document carries a picture — the scan itself, the first page of a PDF, or, for a link you scanned, whatever image the web page offered up. That last one is often wrong: many pages hand out a share card or a logo rather than a picture of the thing.
Iconify draws a new one. Open the document, press ⋯, and choose Iconify — the same word and the same button the app uses for an inventory item. The new picture takes half a minute or so to arrive; the row says "Iconifying…" until it does, and it keeps saying so if you leave the screen and come back.
It works whether or not the document has a picture already, including documents showing nothing at all.
Where the new picture shows up. For a scanned link, it replaces what you see — the page's own image was only ever a thumbnail. For a scan or a photo, the new picture becomes the small one you see in lists and cards, and the original stays on the detail page: Iconify never paints over the thing you actually photographed. That's the same rule inventory items follow.
Iconify is not Rescan. They sit next to each other and do opposite things:
| What it does | |
|---|---|
| Rescan | Re-reads the picture that's there, looking again for text, items and details |
| Iconify | Replaces the picture with a new illustration |
So for a scanned link whose thumbnail is a share card, Rescan just re-reads the share card. Iconify is the one you want.
Two other ways to change it. The same ⋯ menu offers Remove picture — which clears it and lets the plain type symbol come back (a globe, for a page you scanned) — and Use an existing image…, which points this document's card at a picture already in your library. The picker only shows documents, and only those with a picture — a PDF offers its first page, a spreadsheet or Word file nothing: an inventory item's photo belongs to that item's card, not to this one.
On a document shared with you at Can edit, Use an existing image… and Remove picture are in the same ⋯ menu. The picker shows your library — not Radar exhibits or things others shared with you, whose pictures aren't yours to give — and the picture you choose is copied into the owner's copy of the document. It stays there even if you delete your original. Iconify stays with the owner, because the drawing is made with the owner's credits. View only gets none of these.
#Changing a Document's Type and Tags
The type says what a document is — receipt, manual, warranty, certificate, contract, product, guide, note or other — and tags are the short words it's found by. The AI picks both when the document arrives; you can correct either.
- iOS: open the document, tap the pencil (Edit details), and pick a type or add and remove tags under the notes. Save.
- Web: press the pencil in the document panel, or ⋯ → Edit details on a document's own page.
Tags are kept the way search stores them: lower-case, at most 30 characters each, ten per document, so "Garage" and "garage" are one tag.
The owner and anyone with Can edit access get the same controls; View only gets none.
Text documents (notes, plain text, spreadsheets) have no type control — their tags sit under the words in the text editor. Help guide, web page, bio and exhibit are kinds the app makes itself, so you can't change a document into one; ask the AI to save a page or update your bio instead.
Pages are a different thing. A document must keep at least one page — to get rid of one entirely, delete the document. Adding extra pages to a scan or photo document works today: use Add pages on the page strip.
#Repointing a Saved Page
A page you scanned or saved is a bookmark, and like any bookmark it can be aimed at the wrong place — the tag was reprinted, the article moved, or you kept the tracking-laden link somebody sent you.
Change the address. On the phone, open the document, press ⋯ → Edit details and the Address box sits under the name. On the web it's the same box in the edit panel, or ⋯ → Edit address… on a document's own page. Type the new address and save.
What the app does to what you type. It tidies the address before storing it: the #section part and tracking parameters such as utm_source are dropped, and the rest is put in a consistent order. This is not cosmetic — that tidied form is how the app recognises the page, so the next time you scan that tag it finds this document instead of quietly creating a second one. Your original text is kept, and it's what you'll see next time you open the editor.
If the address is already taken, the app says so and names the document that has it, rather than leaving you with two records for one page. Open that one, or delete whichever you don't want, and try again. An address that isn't a web address (anything that isn't http/https) is refused the same way — your document is left exactly as it was.
What changing the address does not do. It doesn't re-read the page, rename the document, or replace the picture. Your title, notes, folder and tags are yours and stay put. If you want the picture refreshed for the new page, use Iconify afterwards.
#Known Limitations
- Maximum file size is 100 MB per upload. Large presentations and image-heavy documents are fine.
- Very large PDFs (over ~15 MB) skip AI visual analysis. They still upload and become fully searchable — the text is extracted and summarized — they just don't get the vision-based content detection (receipt/manual/contract) that smaller PDFs get, which is what the AI matches against when you ask for "my warranties".
- Photographed pages aren't text-searchable yet. Pages you add as photos can be looked at by the AI — ask for a page and it reads it — but their text isn't extracted into search the way a PDF's is. Searching for a phrase you know is on page 7 won't find it; asking the AI to read page 7 will.
- Handwritten documents have lower AI accuracy. The AI does its best with handwriting, but typed or printed text is significantly more reliable. If the AI misreads something, you can edit the extracted text manually.
- PDF text extraction depends on PDF quality. Scanned PDFs (essentially images) are processed through OCR, which works well but isn't perfect. Native-text PDFs extract cleanly.
- Filter by format. Documents are sorted by what they're stored as — CSV, TSV, PDFs, Notes, Office, Images — and each card carries the same word as a badge, so the row you filter by and the label you read agree. A format only appears once you actually have a file of that kind. There's no "Receipts / Manuals / Warranties" row: what a document means is something the AI works out and searches on for you, not a shelf you have to file it on.
- Turn a spreadsheet into inventory. Open a
.csvor.tsvand tap Create items (the table-arrow button, top right on iOS and web). That hands the file to chat with the request already written — press send and the assistant shows you which column it thinks is the name, the brand, the price, and so on. Approve it and the rows become items. It remembers the layout, so the next export from the same source imports without asking again. Duplicates are skipped, and "undo that" puts the whole import in Trash in one go. - Spreadsheet size limit. CSV and TSV files are capped at 25 MB (other files at 100 MB) because every row is read and indexed. A CSV that won't upload is usually one that should be split.
- Office files are read for their text, not rendered as pages. Uploaded Word/Excel/PowerPoint files have their text extracted so they're searchable, but they don't get a page-image preview — open them with the Download action to see the original formatting. Password-protected Office files can't be read.
- Old Office formats (
.doc,.xls,.ppt) can't be uploaded — save them as.docx/.xlsx/.pptxfirst. These are the pre-2007 formats, and despite the similar names they're built completely differently from the modern ones, so renaming the file won't work. Open it in Word, Excel, PowerPoint, Pages or WPS Office and use Save As to pick the modern format; printing to PDF also works. The app tells you this when you try, rather than accepting a file it can't read the text out of — a document nothing can read is one your AI can never find. - Receipt extraction is optimized for US retail formats. Receipts from other countries or highly stylized formats may have lower extraction accuracy.
- Find in document isn't offered in the editor, or on a spreadsheet shared with you, yet. It searches notes, checklists, text and Word files, the text of PDFs and scans, and every row of your own spreadsheets, while you read.
- Same image, same document. If the same uploaded file shows up twice (for example, a chat upload that was also queued for inventory scanning, or a retried scan job), only one document is kept. Earlier builds occasionally produced duplicates — if your document count looks inflated, you can delete the extras from the documents list directly.
#Version History
| Version | Date | What Changed |
|---|---|---|
| 66 | 2026-11-09 | One-tap 👍 / 👎 on every document tile and row — the same thumbs pill as the document's header, iOS and web (AMB-3121) |
| 65 | 2026-11-07 | Scanned receipts now go in a Receipts folder, filed in folders that match their items' Inventory folders and moving when the items move (on by default); a Hide the Receipts folder switch sits beside it in App Behavior. AMB-3028 |
| 64 | 2026-10-29 | Printing a document or saving it as PDF now includes its Description and Notes above the document. A document someone shared with you prints without them: they are the owner's own. AMB-2842 |
| 63 | 2026-10-29 | On iPhone, moving several documents to Trash now goes in one step, so you get one "moved to Trash" message and one notification, even on a slow connection. AMB-2838 |
| 62 | 2026-10-29 | On iPhone, a document that can't be moved to Trash now comes back into Documents, and ambientChat says why. Before, it disappeared from Documents with nothing said, although it was not in Trash, until you restarted the app. Moving several documents at once now says it once: for example "2 documents moved to Trash. 1 couldn't be moved." with the reason. AMB-2832 |
| 61 | 2026-10-29 | A document's Notes and Description now show again after you reopen it — on iPhone, on the web, and to AI assistants reading your documents. They were always saved; the document view just wasn't showing them back. They stay yours: people you share the document with don't see them, and neither does a file they export. AMB-2821 |
| 60 | 2026-10-29 | On the web and the iPhone, renaming a folder or a document that does not save says why and offers Try again with what you typed AMB-2799 |
| 59 | 2026-10-29 | Undo, redo, filing a shared document, creating one and moving one say why in our words when they fail, never the server's own text, on iPhone and the web AMB-2798 |
| 58 | 2026-10-29 | On iPhone, a document change that could not be saved no longer stays on screen after the message says so: the document shows what is really saved AMB-2793 |
| 57 | 2026-10-29 | A document save the server failed on says "couldn't save" in our words, never the server's internal error text, on the iPhone and the web AMB-2789 |
| 56 | 2026-10-28 | A document shared with you whose share lapsed or whose owner deleted it says so, with who to ask, on every screen that opens or saves it, on iOS and the web, instead of "Document not found" or the server's own sentence AMB-2784 |
| 55 | 2026-10-28 | A note's versions and a shared list's changes say who made a change in the same words as an item: "You, via chat", "Grok, for you", "Shared with you: Kathy, via ChatGPT" AMB-2757 |
| 54 | 2026-10-27 | Steps now name the tabs the app has today — Context → Docs and Control — instead of the retired "My Things" and "Account" AMB-2584 |
| 53 | 2026-10-24 | Someone with Can edit on a shared document can give it a new picture from their own library (⋯ → Use an existing image…), on iOS and the web. It is copied into the owner's copy and stays even if they delete their original. Iconify stays the owner's. AMB-2353 |
| 52 | 2026-10-19 | Find reaches wide tables — Find in document now finds words in a wide table on iOS and the web. On a phone, where each row is drawn as a card, a column name is found on each card that shows it, and the hidden header row no longer adds matches you can't see. On a wider screen the table slides sideways to bring the match into view AMB-2168 |
| 51 | 2026-10-19 | On the web, clicking a document's picture opens it full screen and zoomable, paging through all its pages, instead of opening the file in a new tab. AMB-2154 |
| 50 | 2026-10-11 | Every document shows where it's filed — a clickable folder path under the title, on iOS and the web, while reading and editing, with Move… beside it; the assistant names the same whole path AMB-1965 |
| 49 | 2026-10-09 | Find on spreadsheets searches every row — CSV, TSV and every sheet of an Excel workbook, on iOS and the web; the table shows the rows that match and the count is the whole file’s AMB-1936 |
| 48 | 2026-10-09 | Find in document — ⋯ → Find in document, or ⌘F on the web: every match highlighted, a "3 of 12" count, and ↑ ↓ to step through, in notes, checklists, text and Word files, and the text of PDFs and scans, on iOS and the web AMB-1935 |
| 48 | 2026-11-08 | A 👍 isn't an edit — it no longer moves a document to the top under Modified or changes its "Updated" date, for you or anyone you've shared it with (AMB-3076) |
| 47 | 2026-11-07 | 👍 / 👎 on documents — thumbs in the document's header, a swipe or ⋯ on a row, or say it in chat; liked documents lead their folder under Favourites (AMB-3066) |
| 46 | 2026-10-24 | A Just me line stays private in old versions after it is reworded or deleted, and in a copy saved from one; restoring an old version with Undo no longer makes it visible to everyone (AMB-2311) |
| 45 | 2026-10-24 | Change a document's type and tags — in Edit details on iOS and the web, for the owner and anyone with Can edit; an editor can also Remove picture. A document can't be turned into a help guide, web page, bio or exhibit (AMB-2384) |
| 44 | 2026-10-21 | A shared document no longer shows Add pages or the page ✕ to someone it was shared with — those controls could only fail; pages stay the owner's, like the picture (AMB-2266) |
| 43 | 2026-10-21 | Links agree both ways. An item's Documents section now lists the receipt that lists the item, and any document that names it, as the receipt already listed the item (AMB-2258) |
| 42 | 2026-10-21 | Linked items agree everywhere. A receipt now lists the same linked items on iPhone and the web (the web used to miss items only the receipt's lines pointed at), the phone shows each price in its own currency instead of always "$", and a connected AI reading a document gets the same list (AMB-2251) |
| 41 | 2026-10-20 | Web: a document opened from a chat answer now shows its Linked Items too, as it already did from the Documents tab and on iPhone (AMB-2219) |
| 40 | 2026-10-20 | Document details on the web show the time too — Added and Updated each read like "Oct 19, 2026, 9:41 AM", as on iOS, so two dates on the same day are told apart (AMB-2141) |
| 39 | 2026-10-20 | List view on the web shows each document's summary under its details, as iOS does — yours, and ones shared with you or filed into your folders (AMB-2147) |
| 38 | 2026-10-19 | A note shared with you has its version history too — tap its V tag to see the owner's saved versions, and save one as a copy in your own documents. A line someone else has marked Just me is left out of them too (AMB-2046) |
| 37 | 2026-10-19 | Web document details show the Updated date beside Added, as iOS already did — so the date a folder row shows is there when you open it (AMB-2110) |
| 36 | 2026-10-16 | A receipt shows the same date on iOS and the web — its thumbnail used to read "Scanned …" on iOS and "Updated …" on the web; every document now says Updated everywhere, and the List row's line is spaced the same on both (AMB-1932) |
| 35 | 2026-10-13 | Go back to an earlier version — tap a note's V tag to see every saved version (who saved it, via which AI app, when), preview one, and save it as its own document (AMB-2036) |
| 33 | 2026-10-13 | Documents shared with you show their size too — in every view, on iOS and the web — next to whether you can view or edit them. A shared folder sorted by File size now shows the sizes it sorts by, documents in a shared folder say what format they are (PDF, Word…) instead of just "Document", and the List row says the same thing on your phone and on the web (AMB-1953) |
| 32 | 2026-10-10 | Thumbnails show each document's size too, on a line of its own, on iOS and the web — so every folder view now does. An edited note shows its real size: notes used to keep the size they had when blank (often "12 B") however much you wrote (AMB-1950) |
| 31 | 2026-10-09 | An uploaded PDF prints in one click on the web too — straight to your print dialog, like every other document (Safari still opens it first) |
| 30 | 2026-10-08 | Print on the web is one click — it opens your browser's print dialog directly, with a "Preparing to print…" note while it gets the page ready, instead of a blank tab and then a PDF viewer with a second print button |
| 29 | 2026-10-05 | A just-uploaded PDF's preview fills in by itself when page 1 is ready, instead of showing the PDF badge until you reopen it; Export and Print hand over the PDF you uploaded |
| 28 | 2026-10-05 | Recent — one tap shows every document you've added, in every folder and Home, newest first, each saying which folder it's in; on iOS and the web. Replaces Just Added. The chip row no longer disappears in a library with only one kind of file (AMB-1137) |
| 27 | 2026-10-02 | Every format chip fills its first page — Images, PDFs, CSV, TSV and Office now ask the library for that kind of file, as Notes and Web pages already did, so a folder that is mostly PDFs no longer shows an empty Images grid with the photos further down; .md notes count as Notes; agents filter with format (AMB-1568) |
| 26 | 2026-09-30 | Modified pages the whole folder — sorting Documents by Modified now orders every document in the folder, fetched a hundred at a time as you scroll, on iOS and the web, instead of reordering only what had already loaded. The same sort is available to AI apps connected to your library (AMB-1607) |
| 25 | 2026-09-28 | Create items from this… is on every spreadsheet — Excel .xlsx and .tsv as well as .csv — on iOS and the web; it opens chat with the request ready, and the whole sheet imports in one step (AMB-1594) |
| 24 | 2026-09-26 | iOS: a receipt tile shows the receipt's title, the same name the web shows, so renaming a receipt shows on both (AMB-1472) |
| 23 | 2026-09-26 | Web: documents and folders are one tile size, and every document tile has round move, trash and ••• (Share, Rename) buttons — rename or share a document without opening it (AMB-1273) |
| 22 | 2026-09-22 | What an upload costs — Office files, spreadsheets and plain-text notes each cost a few credits for their AI title and summary, charged once even if the upload retries, and never when you're out of credits (the file still arrives under its filename). Plain-text notes had quietly been free; they're now billed like the rest |
| 21 | 2026-09-22 | The format row pages too, and its counts describe the folder — narrowing a big folder to PDFs or Notes no longer fetches the whole folder first, the number on each chip counts the whole folder rather than what you have scrolled, and a format is offered even when none of its documents have loaded yet — on the web as well, where a chip for a format further down a big folder used to be missing altogether. The sorts the phone has to arrange itself still read the folder whole |
| 20 | 2026-09-19 | A big folder opens at once — sorted by Name or Date added, iOS now loads a folder a hundred documents at a time as you scroll, instead of fetching every document in it before showing anything (web already worked this way). The other sorts still read the whole folder |
| 19 | 2026-09-11 | Repoint a saved page — a bookmark you can aim somewhere else, with the app tidying the address so a rescan of the tag still finds the same document, and naming the other document if that address is already taken. Also: Remove picture and Use an existing image…, which the previous version listed as not yet possible |
| 18 | 2026-09-10 | Iconify on a document draws it a new picture — the control the scanned-link guide already promised. Explains how it differs from Rescan, and what still isn't possible |
| 17 | 2026-09-03 | More by meaning — a second section beneath the exact search matches with documents the AI thinks are about what you typed, found from the whole text; counted separately ("9 matches · 4 more by meaning") |
| 16 | 2026-09-02 | Search now covers every document in every folder, including the start of the text inside it, on iOS and web — with a live count under the search box ("9 matches" vs "9+ — scroll for more") instead of a quiet partial answer |
| 15 | 2026-08-23 | Read every page of a PDF — tap a page to open it in the main preview, and the side arrows turn pages before moving on to the next document (previously the preview was stuck on page 1 and the arrows skipped whole documents) |
| 14 | 2026-08-15 | Every document now shows its file size — in its details, on List and Text-list rows, and as a working File size sort (it previously sorted everything as equal because nothing recorded a size) |
| 13 | 2026-08-15 | Adding an image to a Documents folder now FILES it — type, date, folder — instead of scanning it into inventory items; use Scan when you want the things in a photo catalogued |
| 12 | 2026-08-10 | Edit notes, .txt, .csv and .tsv in the app — spreadsheets open as a table and edit as text, with quoting help, a clear reason when a file is too big to edit, and "undo that edit" restoring the previous file exactly |
| 11 | 2026-08-05 | Combine — gather separately-uploaded photo pages into one multi-page document from Select mode (iOS + web) |
| 10 | 2026-07-28 | Turn a spreadsheet into inventory items — "Create items" on any CSV/TSV, with a column mapping you approve once per file layout, duplicates skipped, and one undo for the whole import |
| 9 | 2026-07-28 | .tsv files upload too, and the format filter row only shows the formats you actually have |
| 8 | 2026-07-28 | Upload .csv spreadsheets — table preview, searchable contents, and a new format filter row (CSV / PDFs / Notes / Office / Images) |
| 8 | 2026-07-28 | PDF page previews shown in the same PAGES strip (read-only), with an honest count on long files |
| 7 | 2026-07-27 | Multi-page documents — add photographed pages to one document, view/remove them, ask the AI to read a page (iOS + web + chat) |
| 6 | 2026-07-09 | Upload limit raised 20 MB → 100 MB; very large PDFs degrade to text-only (skip vision analysis) |
| 5 | 2026-07-09 | Upload Office files (.docx/.xlsx/.pptx) — text extracted + searchable, on mobile and web |
| 4 | 2026-06-07 | Terminology: "Admin Web" → "Web" (the web interface) |
| 3 | 2026-05-27 | Updated MCP tools section with current tool names + full tool list (AMB-188) |
| 2 | 2026-05-02 | Note same-image dedup (AMB-106) |
| 1 | 2026-03-01 | Initial guide |