soma

Anyone can make a hundred ads. Nobody knows which one wins.

Generating creative is solved — hundreds of variants in minutes. The bottleneck is knowing which will perform before you spend on it. Soma reads how a brain actually watches each cut, and finds the winner.

TRIBE z-scored BOLD, baseline-subtracted (0 = black screen)
Attention (dorsal)
where the ad holds the eye
Surprise (ventral)
the jolt of something unexpected
Comprehension (association)
where meaning gets built
Weak spot · a sustained stretch where attention sits below this cut’s own median — 2 here

Compare across the batch.

Dorsal attention network · TRIBE z-scored BOLD, baseline-subtracted (0 = black screen)

Attention isn’t one thing. Different regions do different jobs.

Generic eye-tracking tells you where a gaze lands. Soma reads the cortex itself — and two networks matter, each measured separately. This is the distinction the rest of the read-out is built on.

Dorsal attention
IPS · FEF · superior parietal

Where focus is steered — the top-down system that decides what the viewer looks at and holds on.

Ventral · surprise
anterior insula · ACC

The salience network — it fires on the unexpected. This is what registers a hook: not attention in general, but the jolt of something the brain didn't see coming.

Because the two are read from different cortex, Soma can tell a steady, focused ad from a startling one — and score them on the axes that actually drive a hook. A gaze heat-map can’t make that call.

The first three seconds are everything.

Every ad’s first 3 seconds are scored as its hook — separately from the full video, and worth 40% of the total. The ventral surprise signal is what measures it: a hook works by being unexpected, and the salience network is what registers the unexpected.

Ventral salience network · TRIBE z-scored BOLD, baseline-subtracted (0 = black screen)
Product First · rank 1 of 5
hook window averages −0.030 vs baseline
Weak Open · rank 5 of 5
hook window averages −0.075 vs baseline
Hook · Product First
rank 1 · 40% of the total
Hook · Weak Open
rank 5 · 40% of the total
Same product, same length, same batch. The two cuts separate inside the first three seconds — and the hook score is measured on exactly that window, before the rest of the ad gets a chance to recover it.

Did the brand actually land?

A held gaze is worthless if the product never registers. Soma reads the ad's own words — on screen via text recognition, out loud via speech recognition — and when the campaign is named and the language cortex confirms it registers, the score rises.

Every batch makes the model sharper.

Soma turns brain-response into the metrics you actually buy on — attention, retention, the odds a cut performs. Every batch of customer ads ingested grows the dataset behind that translation. The read-out is the product; the growing corpus is the moat.

Ads processed
and counting, every batch
Advertisers indexed
the corpus behind the model
The neural model is public. The edge is the layer between neural signal and real ad performance — and it’s trained on data that arrives with every customer.

Stop guessing which ad wins.

5 clips, ranked and diagnosed. Send us your batch and see where your attention goes.

Create your account