Attachments and @mentions

Nomi works from what you show it: a photograph of the product, an ad whose look you want to borrow, a picture already in your Library.

Getting a picture onto a message

Press the paperclip beside the field. Select a reference opens a panel with a Library tab and a Saved tab, and Upload opens the file picker. A third row holds the product, with its face and name, and opens the product list, on New task and inside a session alike.

You can also drag a file onto the composer or paste one into the field. Everything attached shows as a thumbnail above the field, with an × to remove it.

On the Saved tab your Swipe file folders sit above the ads. The + on a folder puts the whole folder on the message: it shows as a small pill with the folder's name and how many of its ads go, its newest eight at most, each with its words and Radar's reading. Press + again, or the pill's ×, to take it off. Once the message is sent, the session's context lists the folder as one row that opens onto its pictures.

What Nomi can actually read

Pictures, and documents: a PDF, a Word file (DOCX), an Excel sheet (XLSX), CSV, plain text or Markdown. A document's tile shows the moment you add it and shines while it uploads and Nomi reads it. One Nomi cannot read, such as a locked PDF or an old .doc, is refused there and then with a note naming it.

Nomi reads a document in full with your message. A PDF goes to Nomi whole on the turn it arrives, and after that Nomi keeps its text, so later messages can still point at it. Word, Excel, CSV and text files are read as their text. The session's context lists each document as read, and clicking its tile in the conversation opens the file.

Of images, four formats travel: PNG, JPEG, GIF and WebP. Anything else attaches but does not go, and the message says how many did not come through.

How much fits

Four uploaded pictures per message, about 3.5MB together. A picture too large for its share is made smaller before it goes; one that still does not fit, and any past the fourth, stays behind and the message says how many and why, rather than the message failing.

Pictures named from the Library, from Saved ads or from a product have their own budget: four per message.

You can also name a picture in words. Ask for "the kitchen photo in My assets" or "the ads in my Spring folder" and Nomi looks it up in your Library by its name or its folder and puts it on the message, four at most; when several match, it shows you the list to pick from. It is read as a reference, like anything from the Library tab. Ask about the ads you saved on Radar and Nomi searches just those.

Four documents per message, up to 10 MB each and 20 MB together, with at most 100 PDF pages and about 120,000 characters of text between them. A document that would go past that is refused with a note, and what you already attached stays.

Marking up a picture before you send it

Click a picture you uploaded and it opens at full size. Under the close button is a pen: press it and a toolbar opens at the foot of the screen with two tools.

Annotate is for saying something about one place. Click a spot or drag a box around it, then type what you want done there. Leaving the box empty removes it again, which is how a box you drew by mistake goes away.

Draw is a freehand line. Circle the thing you mean and say what you want in your message: the line points, the message asks. It carries no words of its own.

Undo takes back whichever of the two you added last. Press the pen again and the picture stops answering the pointer, with everything you drew still on it.

A picture with something on it wears a small pen badge on its thumbnail, with the count once there is more than one.

What Nomi sees

What you drew is painted onto a copy of the picture before the message is sent, because that is the only way an image model can be told where. Nomi is told the marks are annotations and never to draw them into the ad.

The instructions you wrote beside each marker travel with the painted picture. If the annotations cannot be applied, the original picture is sent and the message tells you that the annotations did not go through.

The copy is drawn in magenta whichever colour you picked. The colour on the swatch is for telling your own lines apart while you work.

Typing @

Every attached picture wears a small badge: @img1, @img2. Click it to rename the picture to a word you would actually use, like bottle. The number counts through the whole session, so a picture attached to your third message might be @img5, and Session context, the panel at the top right of the session, lists it under the same word. A saved video ad from Radar is @video1, @video2 instead, counted on its own, and Nomi reads it as the video.

Typing @ in the field offers those badges, then the pictures sent earlier in this session, newest first. It does not browse your Library and it does not offer products: it points at what this session already holds, so a name in your sentence always means a picture Nomi has. The one extra row is @nomi, which addresses the agent in a session the whole brand can read. A message there that does not name @nomi goes to the room, and the room takes words only: a message carrying pictures stays in the field until it names @nomi or the pictures are removed.

Typing /

Typing / opens Nomi's skills: /static, /copy, /research and the rest, plus any skill your brand wrote under Skills in the Agent's sidebar. Pick one and it sits in the sentence as a chip, and Nomi does that kind of work without deciding for itself.

/audit with a page's address audits that landing page as a phone and a desktop visitor. Without an address Nomi audits the landing of the product the session is about, and asks when there is none.

What a picture counts as

A picture you upload on its own is read as the thing you are selling, so its shape, packaging, colours and label text stay as they are. If the message also carries a product or a named reference, that upload is read as a reference instead: something for the ad to look like, never the thing it sells. Anything from the Library or Saved tab is always a reference.

The selected products provide context for the conversation. Their pictures are not attached to your messages: Nomi picks the photographs an ad shows while it prepares that ad, from what you asked for and the layout it is built in.

The product selection is saved for the session, including when you remove every product. If saving fails, Nomi tells you. Your current selection still applies to the next message, but it may not survive a reload; select it again to retry saving.