← Back to articles

Different Label, Right Ad: How Vectors Match Ads Across Categories

Different Label, Right Ad: How Vectors Match Ads Across Categories
November 16, 2026by Dariusz Rozmus
AdtechEmbeddingsAgentic-audiencesIabContextualAgentic Audiences

Contextual advertising is an old idea: put the ad next to content it fits. Companies such as Peer39, GumGum and Seedtag built whole businesses on it. Their machine learning models run alongside the DSP, read the page and tell the buyer which pages suit which ad.

Without those models, a buyer mostly has IAB categories. A category says roughly which section of the internet a page sits in. It says little about what the page is actually about, and nothing about how well it fits a particular ad. The new Agentic Audiences spec could change that quickly, because it lets the meaning of the page travel inside the bid request itself, as a vector.

Here is what that looks like on one page and one ad.

Picture a general article on a site for older readers: Technology Grandparents Actually Use: Big Buttons, No Cables. It is not a phone review. It talks about what older people keep asking for: large, separate buttons on the TV remote and on the phone, no fiddly cables and tiny charging sockets, loud and clear sound, one button that calls family.

Now picture EasyCall, a brand that makes exactly that phone: big buttons, a large screen, loud sound, an SOS key. That article is one of the best places on the internet for its ad.

With today's IAB labels, the ad will not appear there. With vectors, it will.

Two ways to describe a page

When a page has an ad slot to sell, the ad auction needs to tell buyers what the page is about. There are two ways to do it: give the page a category, or give it a vector.

A category
One code from a fixed list

The IAB Content Taxonomy is a tree of a few hundred topics. Each page is filed under one of them.

IAB6 Family & Parenting
IAB6-7 Pregnancy
IAB6-8 Special Needs Kids
IAB6-9 Eldercare
IAB19 Technology & Computing
IAB19-6 Cell Phones
In the bid request
"cat": ["IAB6-9"]
Simple and readable, but two pages either share a code or they don't.
A vector
The meaning of the whole text, as numbers

An embedding model turns the text into a long list of numbers: an arrow in a space of meaning. Texts about similar things point in similar directions.

article textembedding model3,072 numbers
Seniors articleEasyCall ad
Not yes or no, but how similar
similarity from 0 (unrelated) to 1 (the same)0.58
The smaller the angle between the arrows, the closer the score is to 1. Any page can be compared with any ad.
The arrows are an illustration: real vectors have 3,072 dimensions (OpenAI text-embedding-3-large). The 0.58 is the measured similarity between the article and EasyCall's ad.

Here is what that difference means for our article and EasyCall's ad, in one picture:

Labels compare boxes
Each page goes into one drawer. An ad only opens its own.
IAB6-9EldercarearticleIAB19-6Cell PhonesEasyCall ad✗Eldercare ≠ Cell Phones
✗ No match
Vectors compare meaning
What the article is about and what the ad is about overlap.
ArticleEasyCall adTV remoteschargershearing aidsbright screensbig buttonsloud soundSOS buttonolder peoplephoneslow pricelong batterylarge screen0.58
✓ Matchsimilarity 0.58 · fit 80%
The words in the overlap are there to show the idea. The model does not match keywords: it turns each whole text into a vector and measures how close the two are.

What labels see

Ad auctions describe a page with a category from the IAB Content Taxonomy, and advertisers pick the categories they want to appear in.

  • The article is about older people, so it is labelled Eldercare.
  • EasyCall sells phones, so it targets Cell Phones.

Eldercare is not Cell Phones. By label, the ad and the article have nothing in common, and EasyCall never gets to bid on a page that practically describes its product.

What vectors see

An embedding model turns a piece of text into a vector: a long list of numbers that captures what the text means. Texts about similar things get similar vectors, whatever words or labels they use. The IAB Tech Lab's Agentic Audiences work proposes sending such a vector with the bid request. We wrote about how that works in Text to Vector to Match.

So we tried it, with one of the most widely used embedding models, OpenAI text-embedding-3-large. We wrote the article, turned it into a vector, turned EasyCall's campaign brief into a vector, and compared the two.

Here is the article. Flip the switch from Labels to Vectors and watch the ad slot:

Matched by label: EasyCall can’t bid here
silverdays.example/living/technology-grandparents-use
SilverDays.
IAB6-9 · Eldercare

Technology Grandparents Actually Use: Big Buttons, No Cables

What do readers in their seventies and eighties want from everyday technology? That it works the first time, every time.

Big buttons

TV remotes have dozens of tiny keys, and phones hide everything behind a touchscreen. Older hands want large, separate buttons: one for the volume, one to call a grandchild.

No cables

Fiddly chargers and small charging sockets are a daily struggle. A charging stand, or a battery that lasts a week, fixes that.

Loud and clear

Loud, clear sound that works with hearing aids, big bright text, and an emergency key that calls family with one press.

By IAB label
Article: IAB6-9 Eldercare
EasyCall targets: IAB19-6 Cell Phones
No match: different labels
By vectors · OpenAI text-embedding-3-large
0.58cosine similarity
Fit 80%
Match: same meaning
We used OpenAI text-embedding-3-large. The cosine similarity between the article and EasyCall's campaign brief is 0.58, a fit of 80% on a 0 to 100% scale. That is a lot: texts about unrelated things score close to zero, and the same brief scores about 0.1 against a typical post on this blog. The article is shortened here; the score is for its full text. SilverDays and EasyCall are fictional.

The article is general. It never names a phone brand and spends as much time on TV remotes and chargers as on phones. But it talks about big buttons, loud sound and a button that calls family, for older people, and so does EasyCall's brief. The labels are different, the meaning is the same, and the vectors pick that up: a cosine similarity of 0.58, a fit of 80%. For comparison, the same brief scores around 0.1 against a typical post on this blog.

That is the whole trick: the match comes from what the page says, not from which box it was filed in.

Under the hood

For the auction, the change is small. The bid request, the message an ad slot sends to buyers, keeps its label and gets one more block with the page's vector:

No vector: the request carries only the label
{
"id": "req-1324",
"imp": [ … ],
"site": {
"page": "silverdays.example/living/…",
"cat": ["IAB6-9"],
"cattax": 1
}}
What the fields mean
id
The ID of this auction.
imp
The ad slot for sale, here a 300 × 600 banner.
site.page
The page the slot is on.
cat
The page's category: IAB6-9 Eldercare. One code, and buyers can only check whether it is on their list.
cattax
Which list the code comes from: 1 = IAB Content Taxonomy 1.0.
With vector: the same request, plus the page's meaning
{
"id": "req-1324",
"imp": [ … ],
"site": {
"page": "silverdays.example/living/…",
"cat": ["IAB6-9"],
"cattax": 1
},
+ "user": { "data": [{
+ "name": "agenticAudience",
+ "segment": [{ "ext": { "aa": {
+ "model": "text-embedding-3-large",
+ "dimension": 3072,
+ "type": [2],
+ "vector": "AEAIPAAgsrwAwK…"
}}}]}]}}
What the fields mean
agenticAudience
The new block from the proposed IAB Tech Lab Agentic Audiences extension. The label above stays as it was.
model
Which embedding model made the vector, so buyers can embed their ad brief the same way.
dimension
How many numbers the vector has: 3,072.
type
2 = contextual: the vector describes the page, not the person reading it.
vector
The page’s meaning: 3,072 numbers packed into one string of about 16 KB.
A trimmed OpenRTB bid request, with the field names we used in our own demo of the proposed IAB Tech Lab Agentic Audiences extension. Buyers that do not use vectors can ignore the new block.

A buyer turns its campaign brief into a vector with the same model and compares the two. That comparison is the 0.58 you saw in the example.

Why this matters

For
Advertisers
LabelsEasyCall targets Cell Phones and never sees this article.
VectorsIt finds pages that talk about what it sells, under any label.
Reach the right pages, not the right boxes
For
Publishers
LabelsAn Eldercare page is invisible to a phone brand.
VectorsThe same page is an 80% fit for EasyCall.
Pages that fit no single box get easier to sell
For
Readers
LabelsA random ad, or one about care homes.
VectorsAn ad for the phone the article describes.
Ads that make sense next to the story

None of this replaces labels overnight. Categories are still useful for brand safety and for broad buys. But a label tells you the neighbourhood, not the street, and vectors tell you the street.

At Appliscale we build the infrastructure behind this: bidders, SSP and DSP integrations, Prebid setups and the data pipelines that turn pages and briefs into vectors. If you want to see how embedding-based matching would work on your own inventory, we are happy to talk.

Share: