Documents — Receipts, Manuals & Files

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 Documents tab in My Things
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/.tsv spreadsheet, 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.

#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.

#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/.tsv spreadsheets, and .md markdown 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 by format (image, pdf, csv, tsv, office, markdown or link — every stored spelling of that kind of file), type, category, and folder. Each document reports its format, and include_facets counts them per format. Pass search for an exhaustive text filter across every folder (title, summary, tags, file name, store, start of the text) — paged, with an exact count
get_document — Get full details — AI summary, linked items, metadata
search_documents — Keyword search across titles, summaries, and content
search_documents_semantic — AI-powered semantic search by meaning
update_document — Update a document's title, description, or tags
update_text_document — Replace the contents of a note, .txt, .csv or .tsv. Send the whole new text, not a patch. Refuses a spreadsheet that doesn't parse rather than saving a broken file
undo_text_update / redo_text_update — Step a text document back or forward through its edit history. For a spreadsheet this restores the previous file, exactly
read_document_rows — Page through a stored spreadsheet's rows without loading the whole file
upload_document — Upload a new document for AI processing
move_document — Move a document between folders
trash_document / restore_document — Soft delete and restore
regenerate_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.

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 — the size sits on the end of each row's meta line, after the format and the date, in both List and Text list views. The Thumbnails view leaves it out on purpose: a tile is mostly picture and title, with little space for anything else.
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.

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

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.
Use folders to stay organized. A few well-named folders (Receipts, Warranties, Medical, Home) go a long way. See the Folders guide for more on organization.

#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

#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 .csv or .tsv shows 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, John is 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.

#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: an inventory item's photo belongs to that item's card, not to this one.

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 .csv or .tsv and 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/.pptx first. 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.
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
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