Point your camera at practically anything and the app will figure out what it is. It's the fastest way to fill your inventory, and it's more than a little bit magical.

#What It Does

Smart Scan is the AI-powered camera at the heart of ambientChat.ai. It doesn't just take photos — it understands what it's looking at. Point it at a barcode and it looks up the product. Point it at a receipt and it extracts every line item, price, and store name. Point it at a shelf full of spice jars and it identifies each one individually.

Everything it recognizes gets added to your inventory automatically, complete with names, categories, estimated prices, and expiry dates where applicable. You scan, it catalogs. The division of labor is quite civilized.

#How to Use It

#iOS App

#Basic Scanning

  1. Tap the Scan tab at the bottom of the screen
  2. Your camera activates with the Smart Scan viewfinder
  3. Point the camera at what you want to scan
  4. Tap the shutter button (large circle at the bottom center)
  5. The screen briefly freezes to confirm capture, then returns to the viewfinder
  6. Your item is uploaded to the server for processing — you'll see a progress indicator at the top of the screen

You can scan multiple things in quick succession. Each capture is queued and processed in the background, so you don't have to wait between shots.

#Barcode Scanning

For products with a UPC or EAN barcode:

  1. Open the Scan tab
  2. Point the camera at the barcode — the viewfinder will recognize it automatically
  3. Tap the shutter button to capture
  4. The barcode is decoded and the product is looked up in a global product database
  5. If found, the item is created with full product details: name, brand, category, image, and often nutritional or ingredient data

Barcodes work best when:

  • The barcode is flat and not crumpled
  • You're close enough that the barcode fills at least a third of the viewfinder
  • The lighting is even (no harsh shadows across the bars)

#Receipt Scanning

For paper receipts:

  1. Lay the receipt flat on a surface (a table, counter, or even the floor works fine)
  2. Open the Scan tab
  3. Position the camera so the entire receipt is visible in the viewfinder
  4. Tap the shutter button
  5. The AI reads the receipt and extracts:
    • Store name and location
    • Date of purchase
    • Individual line items with descriptions and prices
    • Total amount
  6. Each line item becomes a separate inventory entry, and a receipt document is created linking them all together

For long receipts, you may need to take multiple photos. The AI is quite good at figuring out what's a product name and what's a tax line or subtotal.

#Photo Scanning (Products & Items)

For anything that doesn't have a barcode, or when you want to scan multiple items at once:

  1. Open the Scan tab
  2. Point the camera at the item or group of items
  3. Tap the shutter button
  4. The AI analyzes the image and identifies what it sees
  5. Each detected item becomes an inventory entry

Multi-item detection is one of Smart Scan's best tricks. Take a photo of your medicine cabinet, a shelf of pantry items, or a collection of tools (or six album covers laid out on the rug), and it will try to identify each item individually. One photo, many inventory entries.

#Per-Item Photos, Cropped Automatically

When you scan a group of items in one photo, each item gets its own cropped photo — the AI locates every item in the frame and the app cuts out just that item's region. Your Crosby, Stills & Nash record shows its actual cover, not the whole floor. The original group shot is kept too, on the scan's source document, and the "Scanned with N others" strip on any item shows its scan-mates with their own crops.

A few things worth knowing:

  • When the crop is good, it becomes the item's picture everywhere — the grid thumbnail, the detail page, chat context. No stylized icon is generated for that item (which also makes the scan faster and cheaper).
  • When a crop can't be trusted — cluttered scenes, partly hidden items — the app plays it safe and keeps the group photo for that item rather than showing you a bad crop.
  • Want the illustrated look instead? Tap Iconify on the item's detail page and the app draws its stylized 3D icon on demand. Iconify replaces the thumbnail; the photo stays on the detail page.
  • Sideways photo? Photos taken pointing straight down (flat-lays) occasionally come out rotated — gravity gives the camera no clue which way is up. The app reads the items' own text to guess the right orientation, and if it still gets it wrong, open the item's ⋯ menu and use the Rotate row: two arrows, one anticlockwise and one clockwise, turning the photo 90° a tap. A spinner covers the photo while the new version is prepared. The fix shows up on every device.

#Saving Scans into a Folder

Above the shutter you'll see Save to folder? with chips for your recently used folders, a Browse button, and Skip — AI decides. Pick a folder (or create one — you can nest folders, like Music/Vinyl) and every item from your scans lands there, visible on the Inventory tab. The chip stays armed for back-to-back scans, so cataloging a big collection is: pick folder once, then shoot, shoot, shoot.

Already saved something and want it somewhere else? The Saved confirmation that slides up carries a Change button — tap it to pick a folder and the item moves. No need to decide before you shoot.

#Your Scan Session Stays Put

A scan mode — AI Lookup, Radar, Add Items — is a session. Ask the AI about something you've just scanned and you'll land in Chat; come back to Scan and your cards, your captures, and your chosen folder are exactly where you left them. Nothing is thrown away and nothing needs re-scanning.

Two things end a session deliberately:

  • Tapping the ✕ in the corner of the mode.
  • Tapping the Scan tab while you're already looking at Scan — the app-wide "tap the tab you're on to go back to the top" gesture.

Anything else — switching tabs, taking a phone call, opening a document — leaves it running. The camera itself does shut off while you're away (it's the biggest battery draw on the phone) and wakes up when you return.

#AI Lookup Keeps Nothing Unless You Say So

AI Lookup is for asking, not filing. Point it at something on a shelf, ask what it is, ask whether it's any good, ask what it costs — and walk away with nothing added to your inventory.

To make the answer instant, the app does create an entry the moment you press the shutter, so the AI has something to talk about. But that entry is invisible: it isn't in your inventory, it isn't in your counts, and it won't turn up in search. It's a scratchpad, not a record.

Save is what turns it into a real one. Tap it and the item becomes yours, with everything the AI worked out — brand, category, barcode, passport — already attached.

Don't tap Save and the capture is thrown away, along with its photo, the moment the card goes: when you dismiss it, when it scrolls off the bottom of a long session, or when you close the mode with ✕. If the app never gets the chance — you force-quit it, or you're out of signal — a tidy-up on our side clears it within a few hours instead. Either way, a shop you browsed doesn't end up living on our servers.

Add Items is the opposite and always has been. Everything you scan there is kept, immediately and permanently. Nothing on this page changes that.

Ask the AI about it later? Yes — the question and the answer are saved to your chat history when the card goes, even though the item isn't. "What was that lens I looked at yesterday?" still works.

#Camera Controls

  • Flash toggle — Tap the lightning bolt icon to cycle the flash on or off. Useful in dim environments.
  • Help overlay — A rotating overlay appears briefly every cycle (10 seconds visible, then fades for 40 seconds) showing you what Smart Scan can detect: Receipts, Products & Items, and Barcodes. It's a gentle reminder, not a demand for attention.

#BLE Tag Scanning

There's a separate scanner for Bluetooth Low Energy (BLE) tags — small wireless tags attached to physical products that carry Digital Product Passport (DPP) data.

  1. From the Scan tab, tap the Bluetooth icon in the top corner
  2. The BLE tag scanner opens, searching for nearby broadcasting tags
  3. Detected tags appear in a list with signal strength
  4. Tap a tag to read its product data and add it to your inventory

This is a specialized feature — you'll only use it if you encounter products with BLE-enabled tags (common in retail pilot programs and smart packaging).

#What Happens After You Scan

  1. Immediate: The scan is submitted to the server. You'll see a brief "Submitting..." indicator.
  2. Processing: The server analyzes the image using AI. This typically takes 5-15 seconds, depending on complexity.
  3. Complete: New items appear in your inventory under a "Just Added" section. A notification confirms what was found.
  4. Documents: A source document (receipt, product scan, etc.) is also created and linked to the inventory items. You can find it in the Documents sub-tab under Context.

You can keep scanning while previous items are still processing. The app handles the queue gracefully.

#Where the Scan Was Taken

When the app can tell where you were when you scanned — because you're standing near a registered iBeacon, the photo carries GPS in its EXIF metadata, or your phone's location is on — that scene gets stamped onto every item the scan creates as Last seen.

Precedence (strongest signal wins):

  1. Beacon — most precise; pins items to a specific Zone you’ve registered.
  2. EXIF GPS in the photo — accurate to where the photo was actually taken, even if you've since walked off.
  3. Your current device location — falls back here when the photo has no GPS.

If none of those is available — say you've denied location permission and there's no beacon nearby — the scan still works, items just don't get a "Last seen" stamp. Nothing breaks. You'll just lose the ability to ask "what's in the kitchen?" for those particular items.

#Web

You can add things from the web interface at app.ambientchat.ai too — by upload rather than a live camera:

  1. Open the Scan page
  2. Click Choose Files and pick one or more files — images, PDFs, Office files (Word .docx, Excel .xlsx, PowerPoint .pptx), .csv/.tsv spreadsheets, plain text and .md notes are all accepted, the same set the Documents tab takes. Up to 100MB each, or 25MB for spreadsheets and .csv/.tsv files, which are read row by row
  3. Pick a destination folder (defaults to My Documents)
  4. The AI processes each file and creates inventory items and/or documents, just like a phone scan

You're told where they're going. When the batch finishes you get one message naming the destination — "Uploaded 3 files to Receipts — processing" — rather than a count on its own. If anything couldn't be used you get one line at the end saying which and why, marked as a problem rather than a success, and the rest still upload.

One caveat worth knowing: that names the folder you sent them to. Processing runs in the background afterwards, and if a photo matches something already in your library it's filed alongside that instead — so on rare occasions the finished document ends up somewhere other than the message said. Open the folder to see where things actually landed.

On a phone browser you'll also see Take Photo and Photo Library buttons; on desktop there's no live camera, so use Choose Files.

#Via Chat

You can also add items through conversation:

  • "Add a bottle of olive oil to my inventory"
  • "I just bought 3 AA batteries at Walgreens for $8.99"

The AI will create inventory entries based on your description. It's not as rich as scanning (no barcode lookup, no image analysis), but it works in a pinch.

#Via Claude Desktop (MCP)

Through the MCP connection, you can use:

  • ambientchat_process_image — Submit an image URL for scanning and inventory creation. Works with product photos, receipts, and barcodes.

Example: "Process this image of my grocery receipt and add everything to my inventory."

#Scanning a Web Link — a Page You Can Name, and Ask About

Not everything you scan is a product. A QR code on a poster, on a demo tag, or on a smart label often holds an ordinary web address rather than a product barcode. Point AR or Radar at one and you get a card for the page, not a guess at a product.

The card tells you what the page says. If the page turns out to hold live data about a thing — a case in a freezer, a shipment, a passport — the card shows a line under the title with what it says right now: what the thing is called, where it is, and its current reading. Most pages carry words rather than readings, and those cards look exactly as they always have: a title and nothing under it. When a handful of things share one page, the card names the first and says how many more there are; when a page turns out to list dozens, the card says nothing rather than pick one out of the pile and call it yours — tap AI and ask, and you get the lot.

You get this on the AR card and on Radar — the two modes that show a card for an address. Lookup builds its cards from a photo rather than from an address, so there is no page behind them to report. On any of them, tap AI and you get the reading in full, as you always could.

On Radar the line appears a moment after the card, and on AR a moment after the picture: the app reads the page once and the card, the answer and the spoken narration all use that one reading, so they can never tell you different things about the same tag.

Where a great many tags are in range at once, Radar reads the pages of the nearest twelve. Each read is a request to whoever runs that page, and Radar is looking every couple of seconds, so it stops there rather than reading a whole warehouse on someone else's behalf. Past the twelfth, a card shows its title and nothing under it — the same as a card whose page simply has no readings, which means right now there is no way to tell those two apart from the card alone. Walk closer and the tag moves up the list and gets read.

Save keeps it as a document. It lands in your documents, not your inventory — because it is a link, not a thing you own. From there it behaves like any other document: rename it, give it your own thumbnail, file it in a folder, share it.

Your picture wins, the same way your name does. Give a kept page a thumbnail — one you upload, or one the app draws for you with Iconify — and that is what you see the next time you scan its tag, in AR, in AI Lookup and on Radar. Pages usually hand out a share image of their own; yours outranks it. Clear the thumbnail and the page's own image comes back.

It looks like what it is, and it opens. A kept page wears a Link badge with a web icon, so you can pick it out of a list of PDFs and receipts at a glance. To go back to the page itself, open the document and choose Open page from the ⋯ menu — on your phone it opens in your browser, on the web in a new tab.

Your name for it sticks. Rename it to something that means something to you — "Chicken Wings 12 oz" instead of whatever the page calls itself — and every later scan of that same tag shows your name. Scanning the same address twice never makes a second copy; it finds the one you already named. That holds whichever way you met it — scan it in AR, or keep it from a Radar exhibit whose link points at the same page, and it is one record either way. A page kept from Radar still lives in your Visits journal under the venue and zone where you found it; it just also answers to its address, which is what lets your name for it follow you.

AI and Listen read what the page POINTS AT. This is the part that matters for a smart label. Tap AI or Listen and the assistant looks at what the page holds right now — a current temperature, a red alert, a delivery date — not just its title. Ask "is this still good?" of a chilled-goods tag and you get an answer about the actual reading, the zone it is sitting in, and the chain of places it came through. Info opens the page in full.

AI hands the page to chat and opens with "What's this?" Tapping AI drops you into Chat with the page attached — a thumbnail chip with its name on it, exactly like tapping the speech bubble on an item or a document — and asks one short opening question for you. The answer is usually already waiting, because it is prepared while you are still looking at the card.

There is no wall of text in your own message: just the picture and four words, and then it is your turn. "Is this still good?" or "where has it been?" is answered from the reading, not from a guess, because the assistant has the page itself in front of it. A page you have already kept brings your title and your notes along too.

The picture is not part of what the assistant is asked about. It is how the app labels the link, so the answer is about the thing behind the tag rather than about an icon.

Listen waits for the page rather than talking over it. Tap it the instant a card appears and it still speaks about the reading — it reads the page first if nobody has yet. That is worth knowing because a narration cannot go back and check: unlike AI, it gets one look at the page and then speaks, so what it is told is all it has.

Listen explains rather than reads out. It says what the state means — a temperature against what is normal for that kind of thing, a status against what it implies, a trend across wherever the thing has been — and then what, if anything, you should do about it. It names the subject out loud and restates the facts it is reasoning from, because you are usually looking at the thing rather than at your phone.

It starts talking straight away, and you can stop it. The narration is spoken a sentence at a time as it is written, so you hear the opening words while the rest is still being made rather than waiting for the whole thing. While a card is talking, its Listen pill becomes a Stop square — tap it and the narration ends there. Only the card actually speaking shows it, so in a list of cards you can see which one you are hearing. Starting a narration on another card stops the first one rather than queueing behind it.

And it is written down. Every Listen in AR is saved to your Q&A history, with the words that were spoken. Find it later on the myAI Context → Q&A tab, or on the web, under the name the card was carrying — so a narration you half-heard while your hands were full is something you can go back and read.

That works even on pages that look empty to a machine. Plenty of modern sites — anything built with a site builder, most marketing pages — send an almost blank document and then draw the real content in the browser. Where the data is reachable, the assistant reads it from where the page keeps it rather than giving up at the title.

A few honest limits:

  • Some pages still cannot be read. Sites that show a "checking your browser" interstitial, or that fetch their contents from somewhere we are not allowed to follow, may yield nothing. When that happens the assistant tells you it could not read the page instead of guessing at what is on it — the card still works, it just knows less.
  • The reading is a snapshot, and it tells you when it was taken. The page is checked when you ask; if it has changed since the last look, you get the new reading rather than the old one. You do not have to wait anything out or ask twice.
  • A reading drawn out of a page's own code is a best effort. It is not a published feed, so a site that reorganises itself can stop yielding data without warning. If that happens the answer falls back to what the page says in plain text rather than inventing numbers.
  • Pages do not get to give orders. Whatever the page says reaches the assistant as quoted material, clearly marked as somebody else's content. A page containing "ignore your instructions" is treated as a page that contains that text, not as an instruction.

#Tips & Tricks

  • Good lighting makes a real difference. Smart Scan can handle imperfect conditions, but well-lit, clearly visible items produce dramatically better results. Natural daylight is ideal; harsh overhead fluorescents are the enemy of receipt scanning.
  • Hold the camera steady for a moment before tapping. The capture is instant, but giving the autofocus a beat to lock on produces a sharper image, which produces better AI recognition.
  • Receipts work best flat and complete. Crumpled receipts, partial captures, or photos where your thumb obscures the total will still work — but results improve significantly with a flat, fully visible receipt. Smooth it out, pin down the curling edges, and your accuracy will thank you.
  • Scan in batches, review later. You don't have to verify every item as it's scanned. Blast through a pile of products, then visit the Inventory tab to review and correct anything the AI got wrong. It's faster and more satisfying.

#Options

Setting What It Does Default
Camera Flash Toggle flash on/off during scanning Off
Help Overlay Rotating tips about what Smart Scan can detect On (cycles automatically)
BLE Tag Scanner Separate scanner for Bluetooth product tags Available via Bluetooth icon

#Known Limitations

  • Handwritten receipts are challenging. The AI can handle printed thermal receipts well, but handwritten notes, invoices, or receipts from very old dot-matrix printers may produce incomplete or inaccurate results.
  • Very blurry or dark images may fail. If the AI can't make out what's in the photo, it will let you know rather than guess wildly. Retake with better lighting or a steadier hand.
  • Maximum of about 20 items per photo. Multi-item detection works well for reasonable groups, but photographing an entire warehouse aisle will hit practical limits. For large collections, take multiple focused photos.
  • Barcode lookup depends on the product database. Obscure, local, or very new products may not be in the global UPC database. In those cases, the AI falls back to visual identification from the photo.
  • Processing requires an internet connection. All image analysis happens on the server, so scanning in airplane mode or areas with no signal won't work until connectivity is restored. The app will queue the scan and submit it when you're back online.
  • Thermal receipt paper fades. This isn't our fault, but it's worth mentioning: if you've got receipts you want to keep, scan them sooner rather than later. The app preserves the data even after the paper becomes an illegible grey smudge.

#Version History

Version Date What Changed
19 2026-09-13 AI opens with a question and the answer is usually already there — tapping AI on a scanned page attaches it and asks "What's this?", prepared in advance so it arrives straight away instead of after a wait; the link's own icon is no longer part of what the assistant is asked about, so answers are about the thing rather than the artwork
18 2026-09-13 Listen starts speaking on its first sentence instead of waiting for the whole narration to be written, and a card that is talking now shows a Stop square in place of its Listen pill — on Radar, Lookup, AR and the nearby-tag card — so a narration you did not want can be ended with one tap
17 2026-09-13 Tapping AI on a scanned page now attaches the page — you land in Chat with a thumbnail chip and an empty box to type in, instead of a paragraph written on your behalf, and the assistant already has what the page says. Listen explains what a reading means and what to do about it rather than just naming it, and every AR Listen is saved to your Q&A history with the words that were spoken
16 2026-09-12 A kept page's own picture reaches its card — the thumbnail you set on a web link shows on the scan card in AR, and AI and Listen both answer from the page the QR code points at
15 2026-09-11 A tag no longer loses its reading to the furniture — Radar reads the nearest twelve tags, rather than the nearest three things, so a tag standing behind a few ordinary exhibits still says what its page says. Past the twelfth the card shows its title alone
14 2026-09-11 Radar shows the reading too — the line now appears on Radar cards as well as AR, drawn from the same single read of the page that the AI and Listen pills use
13 2026-09-11 The scan card shows the reading, not just the name — a tag whose page carries live data now says what that data is on the card itself, instead of making you tap AI to find out
12 2026-09-11 AI and Listen now read pages that look empty — a site that draws its content in the browser used to answer with its title alone; the assistant now reads the data the page holds, including a thing's zone and the chain of places it came through. A changed page is picked up on the next ask instead of having to be waited out
11 2026-09-10 A kept web page now wears a Link badge instead of looking like any other document, and Open page on its ⋯ menu takes you back to the page
10 2026-09-10 Web Scan now accepts every file type the Documents tab does, and names the folder a batch is going to
9 2026-09-08 Keeping a page works the same whichever way you met it — a link kept from a Radar exhibit is the same single record as the one you scan in AR, so your name for it follows you either way
8 2026-09-08 Added "Scanning a Web Link" — scan a QR holding a web address and keep it as a document you can rename, re-illustrate and share; AI and Listen read what the page says now, not just its title
7 2026-09-07 Added "AI Lookup Keeps Nothing Unless You Say So" — the shutter no longer files things; Save does, and un-kept captures (and their photos) are thrown away when the card goes
6 2026-08-12 Rotate now turns the photo EITHER way — two arrows on the ⋯ menu row — and shows a spinner while it works
5 2026-07-29 Added "Your Scan Session Stays Put" — sessions survive leaving the tab; ✕ / tab re-tap end them. Documented Change on the Saved confirmation
3 2026-06-07 Added Web section — uploading photos/PDFs/markdown via the web interface
2 2026-05-01 Added "Where the Scan Was Taken" — beacon/EXIF/GPS precedence, last_seen stamping
1 2026-03-01 Initial guide