Neuromarketing tech / Ecommerce ads

You already make ads with AI.Now give it attention data.

Give Claude or Codex a predicted attention heatmap. Let your AI change the layout, headline or CTA, then compare what stands out in your next campaign creative.

See the result for yourself!

Connect Claude or Codex See the ad comparison

5 free checksNo card. Claude Code or Codex on Mac.

  • See what pulls attention
  • Track each A/B version
  • Measure what performs
Over-the-shoulder view of a customer reviewing two product ad directions with Claude on a laptop at their desk

Your ad versions, heatmaps and attention notes, together in your agent.

Illustrated workflow · Real AttentionProof predictions.

Inside the ad workflow

Two prepared creatives and their recorded attention predictions.

Swipe across to explore.
VELUN ad directions

Use the heatmap to change the layout, headline and CTA.

I made a second direction for VELUN. The bottle is larger, the headline is more specific, and the shopping action stands out.

Here are both ads and their AttentionProof heatmaps:

VELUN ad comparisonInteractive artifact · Version 2
Original VELUN ad with a cobalt serum bottleRevised VELUN ad with a larger serum bottle, Your daily serum ritual headline and Shop the serum call to action

The maps show predicted attention. Test these versions in your ad platform to see which performs best.

attentionproofPredicted attention

VELUN / CREATIVE DIRECTION

Two ways to catch the eye.

One product. A new direction to test.
AOriginal ad
Original VELUN ad with a cobalt serum bottle, with its real predicted attention overlay
Headline
40.2%
Product
19.6%
CTA
8.0%
BAfter the heatmap
Revised VELUN ad with a larger serum bottle, Your daily serum ritual headline and Shop the serum call to action, with its real predicted attention overlay
Headline
27.4%
Product
28.6%
CTA
13.9%

Share of total predicted attention inside each selected region. Layouts and region sizes differ.

Creative files & attention report

velun-original.webpvelun-revised.webpattention-report.json
Keep the evidence. Test the outcome.

Attention predictions, not campaign results.

Share of predicted attention in each selected region. Layouts and region sizes differ. These are attention predictions, not campaign results.

What the percentages mean

Share of total predicted attention inside selected headline, product and CTA regions. The rest falls elsewhere. The layouts and region sizes differ. Test the ads to learn which one gets more clicks or sales.

Product Agent Creative direction

Connect your AI.
Change what stands out.

Let your AI generate a different variant for your campaign. Measure what stands out, then take it into your A/B test.

  1. 01

    Connect your AI

    Copy the setup prompt into Claude Code or Codex. Connect AttentionProof to the AI you already use.

    Connect Claude or Codex
  2. 02

    Let it see the attention

    The original product ad with its calculated attention heatmap

    Give it your ad. Your AI opens the heatmap, sees where predicted attention goes and records what pulls the eye.

  3. 03

    Generate a different variant

    The revised product ad with a larger bottle, a different headline and a clearer shopping action

    Let your AI’s image tools change the layout, headline or CTA for your campaign. Check the new variant and compare what stands out.

Neuromarketing for your AI workflow

See the result for yourself!

Bring one ad. Give your AI the attention data, then ask it for a different creative direction.

5 free checksNo card. Start with your own ad.

Connect Claude or Codex
Already connected?

What the workflow asks your agent to do

Keep the original ad, check its predicted attention, make one deliberate revision, compare both versions and preserve the evidence for your campaign test. Open the setup guide.

Your agent asks for the analysis budget before running checks. Image generation uses the tools available in your agent.

Over-the-shoulder view of a customer reviewing two product ad directions with Claude on a laptop at their desk

Your ad versions, heatmaps and attention notes, together in your agent.

Illustrated workflow · Real AttentionProof predictions.

Inside the ad workflow

Two prepared creatives and their recorded attention predictions.

Swipe across to explore.
VELUN ad directions

Use the heatmap to change the layout, headline and CTA.

I made a second direction for VELUN. The bottle is larger, the headline is more specific, and the shopping action stands out.

Here are both ads and their AttentionProof heatmaps:

VELUN ad comparisonInteractive artifact · Version 2
Original VELUN ad with a cobalt serum bottleRevised VELUN ad with a larger serum bottle, Your daily serum ritual headline and Shop the serum call to action

The maps show predicted attention. Test these versions in your ad platform to see which performs best.

attentionproofOriginal images

VELUN / CREATIVE DIRECTION

Two ways to catch the eye.

One product. A new direction to test.
AOriginal ad
Original VELUN ad with a cobalt serum bottle
Headline
40.2%
Product
19.6%
CTA
8.0%
BAfter the heatmap
Revised VELUN ad with a larger serum bottle, Your daily serum ritual headline and Shop the serum call to action
Headline
27.4%
Product
28.6%
CTA
13.9%

Share of total predicted attention inside each selected region. Layouts and region sizes differ.

Creative files & attention report

velun-original.webpvelun-revised.webpattention-report.json
Keep the evidence. Test the outcome.

Attention predictions, not campaign results.

Share of predicted attention in each selected region. Layouts and region sizes differ. These are attention predictions, not campaign results.

Attention heatmaps for A/B tests

See what each ad makes visible.
Measure what people do.

Keep every creative, AttentionProof heatmap, hypothesis and campaign result tied to the same version ID. Use the prediction to shape the next variant; use Meta or your testing software to measure the outcome.

Your agent records

  • Each ad version and its attention heatmap
  • Where predicted attention concentrates
  • What changed and why it might help

Saved in your chosen project folder, with a version ID for each creative.

Your ad platform measures

  • Click-through rate and purchases
  • Cost per acquisition and return on ad spend
  • Which variant performed best in the test

Add the campaign results to the same version IDs. Campaign data is not imported automatically.

Use the prediction. Keep testing the outcome. A heatmap predicts visual attention. It does not measure gaze, clicks or sales.

Reviews

In their own words.

Leave a review ↗

Selected reviews, shared with permission.

I was making ads with Codex, but something didn’t feel right. Then I gave it AttentionProof MCP and, OMG, it went crazy. I simply asked Codex to update my ad. It changed the layout, CTA size and headline sizing, and I instantly saw and felt the difference. Can’t wait to A/B test.
Alex

Loading reviews…

Your iPhone. Your AI. One balance.

Subscribe on iPhone.
Keep creating with AI.

Choose your plan in the AttentionProof app. Use the same Apple Account to bring your checks to the web, Claude and Codex.

View plans & App Store

Starter

US$19.99/ month

30 checks each month

About US$0.67 per checkwhen you use all 30.

Choose Starter

Pro

US$49.99/ month

100 checks each month

About US$0.50 per checkwhen you use all 100.

Choose Pro
US$0.99 for one extra checkOne-time purchase. No subscription or renewal.

Each ad or variant you analyze uses one check. Unused paid checks do not expire.

Your next creative direction starts here.

Start with 5 free checks.

Bring your first ad. No card or automatic upgrade.

Connect Claude or Codex

US reference prices. Apple shows your local price, taxes and renewal terms before purchase. Monthly subscriptions renew automatically until canceled in Apple subscription settings. Free checks are a one-time allowance per account. Failed analyses return the check. Your agent and image-generation costs are separate.

Before you start

A few clear answers.

What does AttentionProof do, and what does my agent do?

AttentionProof predicts visual attention and returns the heatmap, overlay and attention data. Claude or Codex interprets the result, records the reasoning and uses its available image tools to create revisions. If your agent cannot generate images, it can prepare an editing brief instead.

Does a stronger heatmap mean a winning ad?

No. A heatmap shows what is likely to draw attention. Use it to choose a specific revision, then run both ads in your A/B testing software to measure clicks, purchases, cost per acquisition and return on ad spend. AttentionProof does not run campaigns or import their results automatically.

Where are my ads and attention notes saved?

The ad workflow asks your agent to save the creatives, heatmaps and version notes in a project folder you choose. Your AttentionProof account keeps usage metadata, not a web library of uploaded ads. Keep the version IDs when you add results from your ad platform.

How do I measure which ad performs better?

Use AttentionProof to compare predicted attention, then run both versions in the advertising or A/B testing software you already use. Your ad platform measures clicks, purchases and campaign cost.

What do I need to get started?

Use Claude Code or Codex on a Mac, an AttentionProof account and a product ad to work on. Setup itself uses no checks. Your account starts with 5 free checks; each completed image analysis uses one, including rechecks. Your AI agent and any image-generation costs are separate.

See the result
for yourself!

5 free checks. Give your next ad a different attention pull.

Connect Claude or Codex