Experimentation intelligence, inside your AI assistant

See what the market tested. And what it kept.

ABSee gives your AI assistant 25,000+ real experiments across 4,500+ brands — the page before, the version tested, and whether it was shipped or rolled back. So every hypothesis comes with evidence behind it.

Get a demo Connect your AI
Works withClaudeChatGPTGeminiconnects in seconds

25,000+ experiments across 4,500+ brands, including

How it works. Watch it in under a minute.

  1. 1 Hook

    Lancôme Bestsellers category page with a plain text headerLancôme Bestsellers category page with the header set over a beach-hut campaign image of three productsLancôme
    Karen Millen product page with a black Add to Bag button above PayPal and Apple PayKaren Millen product page with a deep green Add to Bag button above PayPal and Apple PayKaren Millen
    Timberland added-to-cart panel showing a yellow boot, a suede brush suggestion and a View Cart buttonTimberland added-to-cart panel with a new line at the top saying items in your bag are not reservedTimberland
    Timberland membership sign-up pop-up with an offer line and a Sign-up Now buttonTimberland membership sign-up pop-up with a full-width button, an opt-out link and four member benefitsTimberland
    Reebok product page details list with Promotion Exclusions, Best For and Shipping & Returns rowsReebok product page details list without the Best For rowReebok
    AllSaints product page with a heart wishlist button beside Add to BagAllSaints product page with a bookmark wishlist button under the product name and a full-width Add to BagAllSaints
    Zimmermann product page before the testZimmermann product page, tested version: Hides the automated size recommendation tool.Zimmermann

    Your competitors are running experiments on their sites right now.

  2. 2 Ask

    ClaudeABSee
    What have brands tested to stop shoppers leaving at the cart?
    ABSee · search_experiments

    ABSee records them. Ask Claude, ChatGPT or Gemini a plain question.

  3. 3 Results

    ClaudeABSee
    1. Timberland added-to-cart panel showing a yellow boot, a suede brush suggestion and a View Cart buttonTimberland added-to-cart panel with a new line at the top saying items in your bag are not reserved

      1. Timberland · Mini-cart inventory warning addition — Adds an unreserved inventory warning message to the mini-cart. [Kept]

    2. Reformation bag with a Stuff you might like row of products under the itemReformation bag going straight from the item to the order totals

      2. Reformation · Cart page recommendations removal — Hides the suggested-products block from the cart summary [Kept]

    3. Quay cart before the testQuay cart, tested version: Adds shipping, returns and support reassurance by the checkout button.

      3. Quay · Checkout button reassurance messaging — Adds reassurance copy about shipping, returns, and support near the checkout. [Kept]

    4. Patagonia cart order summary with a one-line Ironclad Guarantee notePatagonia cart order summary with a boxed Ironclad Guarantee panel spelling out repair, replacement or refund

      4. Patagonia · Cart page full-copy guarantee panel — Replaces the one-line Ironclad Guarantee note with a full-copy guarantee panel beneath the cart order totals [Testing]

    ABSee · get_experiment

    You get real experiments back: what changed, and what the brand did next.

  4. 4 The card

    Timberland · cart · mobile

    Mini-cart inventory warning addition

    Adds an unreserved inventory warning message to the mini-cart.

    The full screen

    Before
    Timberland added-to-cart panel showing a yellow boot, a suede brush suggestion and a View Cart button
    After: the tested version
    Timberland added-to-cart panel with a new line at the top saying items in your bag are not reserved
    Slide to compare
    Kept

    Observed 138 days; kept.

    Every record shows the page before, the version tested, and the outcome.

  5. 5 The full record

    What changed
    Adds an unreserved inventory warning message to the mini-cart.
    Problem being solved
    Shoppers leaving items in their cart without feeling the urgency to finalize their purchase.
    Strategic takeaway
    Loss Aversion: Explicitly stating that carted items are not reserved leverages the fear of missing out, prompting faster checkout decisions.

    25,000+ experiments. 4,500+ brands.

    Get a demo

    Bring a hypothesis. See what the market already tried.

Research finds the problem. ABSee brings the evidence for the fix.

Set up in a minute

Copy. Paste. Start asking.

No dashboard to learn, no integration project. ABSee plugs into Claude, ChatGPT or Gemini — whichever your team already uses.

01
Copy your ABSee linkOne line. Nothing to install.
02
Paste it into your AI assistantIt asks you to sign in to ABSee.
03
Start asking"What's been tested against fit uncertainty?"

            
    
          
    
          
    ✓
    ABSee is connectedYour AI assistant can now search experiments, outcomes and patterns.
    
        
    
        
    Step-by-step for every assistant →
    
      
    
    
    
  
    

    




    
    
    
      Real pages, real outcomes
      
    
        
    Not case studies. What brands actually ran.
    
        
    Every experiment is captured from the live site — the page shoppers saw, the version being tested, and whether the brand shipped it or rolled it back.
    
      
    
      
    
    
    

    



    

    
  
    
    Ask ABSee
    
    Ask the questions you already ask. Get answers backed by real experiments.
    
    
    
      
    
      
    
    
    
  
    

    

    


    
    
    
      The difference
      
    Generic AI gives you best practice. ABSee adds the evidence.
    
      
    "Should we add a free-shipping progress bar to the cart?"
    
      
    
        
    
          
    Without ABSeeAI on its ownGeneric best practice
    
          Free-shipping progress bars are a proven best practice. They encourage shoppers to add more to reach the threshold, which can increase average order value.
          No outcomes · No examples · Could apply to any site
        
    
        
    
          
    With ABSeeYour AI + Real experiments, real outcomes
    
          
    Brands have tested it in different places. R.M.Williams tested a free-shipping tracker on the full cart page. Aéropostale tested the same idea in the mini-cart.
    
          
    
        
    
      
    
    
    

    





    

    
  
  
    
    UX patterns at scale
    
    Start with the shopper's problem. See how the whole market solves it.
    
    
    Not just A/B tests. ABSee reads the pages brands serve every day across the whole market: which approaches are spreading or fading, who tested first, and the original ideas only a few brands have found.
    
    
    
      
    
        
        
        
        
      
    
      
    
        
    How the market solves itTested first Shipped without a test
    
        
    
          
      
          
    1. Model's height and size on the photoShown beside the gallery or under the price
      Most common
      2. 
          
    2. Fit note under the size picker"Runs small, we suggest a size up"
      Spreading
      3. 
          
    3. Fit summary from reviewsSmall · True to size · Large
      Spreading
      4. 
          
    4. Size finder quizHeight, weight and usual size in, a size out
      Steady
      5. 
          
    5. Size chart in a pop-upA table of measurements behind a link
      Fading
      6. 
        
    
          
    Unique approaches Seen at one or two brands
    • Order two sizes, pay for the one you keepThe second size is free to send back
    • Fit compared to a pair you already ownPick a brand and size you know, get the match
    
        
    
        
        
        
      
    
    
    
  
    

    

    



    
  
    
    Your data, your edge
    
    Market evidence built in. Connect your own data to find the leaks too.
    
    
    
      
      
    
        
    
          Your clickstream · optional
          
    GA4BigQueryContentsquareAmplitude
    
          Finds where sessions drop, on which device, for which shoppers.
        
    
        
    
          Your past test results · optional
          
    WingifyKameleoonOptimizelyDYDynamic Yield
    
          Answers "Have we tested this before?" Private to your team.
        
    
      
    
      
    
        
        
    
          
          Market evidence
          25,000+ real experiments across 4,500+ brands — before & after screenshots, outcomes and the UX thinking behind them.
          Always on
        
    
      
    
      
    
        Your AI assistant
        Claude, ChatGPT or Gemini
        
      
          
    • Where does our funnel leak?
      • 
          
    • What have other brands tried against it?
      • 
          
    • Have we tested this before?
      • 
        
    
      
    
    
    
    
    Your data stays private to your team — it sharpens your answers and is never shared or added to the market evidence.
    
  
    

    



    

    
  
    
    Plans
    
    From what others tested to evidence for your hypothesis.
    
    
    
      
    
        Information
        
    Library
    
        
    What have others tested?
    
        
    • Search real experiments
    • Before & after screenshots
    • Brands and categories
    • Patterns across the market
    
        Get a demo
      
    
      
    
        Decisions
        
    Intelligence
    
        
    What's the evidence for our hypothesis?
    
        
    • Everything in Library
    • Outcomes: shipped or rolled back
    • Evidence for and against
    • UX principles behind each pattern
    • Your clickstream and past tests
    • Competitor tracking
    • Prioritisation
    
        Get a demo
      
    
      
    
    
  
    

    

    


    
  
  
  
    
    
    Ask ABSee
    
    
    Evidence behind every hypothesis. Bring the leak you've found — leave with the evidence for how to fix it.
    
    
    
      Get a demo
      Connect your AI