Pensa: Ecommerce Competitor Research

See how any online store sells: pricing, urgency, social proof and checkout techniques, in the shop's own words. Runs on-device.

Pensa is ecommerce competitor research that runs while you browse. Open any online store, whether it's a competitor, a brand you admire, or a Shopify store you found through an ad, and Pensa names the selling techniques on the page: crossed-out "compare at" prices, free shipping thresholds, low-stock messages, countdown timers, social proof pop-ups, pre-ticked add-ons and fees added at checkout. You get each shop's own wording and the numbers behind it, so you can see exactly how other stores sell, and then build your own version. No more screenshotting product pages and guessing what is going on. WHAT YOU GET • A count on the toolbar. The icon shows how many techniques the page in front of you uses. • The shop's own words, and the numbers. Click the icon to see each technique with the shop's wording and the specifics: "Crossed out $52, 1.5 times the $35 price." "Only 1 left at one nearby store, Polaris: scoped to a single store." • Standouts, pointed out for you. When a shop uses a technique at full strength (a crossed-out price at 1.5 times the real one or more, a stock count of 3 or fewer, a live clock counting down, a pop-up naming a recent buyer), a small card says so as soon as it is on screen. Cards never block the page. You can switch them to standouts plus every add to cart, or off. • How shops build it. Every technique comes with how shops build it and what to note when you compare one shop's version with another's: the size of the gap, what a stock claim is scoped to, where a threshold sits. • Build your own, with an AI prompt. Each finding has two or three plain steps for putting the technique on your own store, and a Make AI prompt button. One click copies a ready prompt for ChatGPT, Claude, Gemini or any AI chat, with blanks for your store's details. The prompt asks for three versions from subtle to bold, where each one goes on the page, how to build it on your platform (settings, apps, or Liquid, HTML and CSS), and an A/B test plan. Every kit builds the version whose claims are true: a real deadline, live inventory, a price you really charged, fees shown up front. • A weekly report. "What Pensa saw this week" collects your research: the most widespread techniques, on which shops, with real examples and the standouts first. Copy it as text for your team, a client or a founder group chat. It never blocks, hides or changes anything on a page. WAYS TO USE IT • Tear down a competitor's product page before you redesign yours • Compare how the shops in your niche show low stock, countdowns and free shipping thresholds • Collect real examples of sale pricing and reference prices for a pricing review • Walk through a checkout to see which add-ons are pre-ticked and which fees appear late • Prepare a CRO audit or a client pitch with each shop's own wording • Keep a weekly record of what the brands you follow do to sell WHAT IT NOTICES: 19 TECHNIQUES On the page in front of you: • Reference prices: a higher crossed-out "was" or "compare at" price next to the real one • Charm pricing: prices that stop just short of a round number, like $39.99 • Limited-stock messages: "Only 3 left" • Countdown timers: sale clocks and other deadlines beside an offer • Live activity notices (social proof): "23 people are viewing this", recent-buyer pop-ups • Preselected options: warranties, protection plans, add-ons and marketing opt-ins ticked in advance • Loaded decline wording: "No thanks, I don't want to save money" • Spend thresholds: "You're $12 away from free shipping", and progress bars toward it • Unequal button emphasis: one choice made far louder than the other • Decoy options: a third option that makes another one look like the obvious pick • Repeated interruptions: pop-ups and interstitials, one after another • Savings framing: the same discount shown as whichever number looks bigger, dollars off or percent off • Exit-intent offers: an offer that appears as you move to leave By comparing one page to the next: • Fees added later: charges that were not in the first price you saw • Unrequested cart items: add-ons in the cart that were never chosen By comparing today to what the same site showed you before: • Timers that reset on each visit • Stock counts that go up as well as down • "Was" prices that have never been the actual price • Viewer counts that repeat or never vary The last four say nothing on a first visit, by construction. They are claims about change over time, and there is nothing to compare against until you have seen the same item twice. HOW IT DESCRIBES A SHOP It reports what a page displayed, never whether it was true. A limited-stock message may be perfectly accurate, and Pensa makes no claim about any retailer's intent. Whether to try a technique on your own store is your call. PRIVACY AND PERMISSIONS Your browser will tell you Pensa can read the websites you visit, and that is accurate: it needs to, because these techniques turn up on small and new shops as often as on big ones, and no list of sites would cover them. What it does with that access is narrow: • It reads a page and decides whether it is a shop first. On anything else (email, news, documents, chat) it stops, records nothing, and stays out of the way. • It never runs on banking, health, government or webmail sites. • There is no account and no sign-up, and no advertising or analytics company is involved at any point. • Out of the box it makes no network requests at all. You can check: open DevTools, go to the Network tab, and browse. Everything it notices stays on your device, and the weekly report is built there too. Detections are deleted after 30 days by default, and you can change that in Settings; the product history that lets it spot a countdown that resets or a "was" price that is never charged is kept up to 90 days. You can export or erase all of it at any time. OPTIONAL: HELP MEASURE THESE TECHNIQUES One setting, off by default and not pre-ticked, shares which shops use which techniques, and whether people added the item to their cart after seeing them, so their prevalence can be researched. It is a high schooler's research project. Pensa asks once, on the page that opens when you install it, with two equally weighted answers and nothing preselected. It does name the shop: a report says "someone saw a countdown on shein.com today." On product pages it also says whether Add to Cart (or Reserve, on travel and ticket sites) was clicked. It never sends the page, the product, your searches, page text, prices, your account, anything that identifies you, or any time more precise than the day. Reports go out in batches, not at the moment something is found, and you can read the exact reports waiting to be sent before any of them are. Turning it off deletes anything not yet sent. CONTROLS Every technique in the list above has its own switch. Turn off anything you do not need for your research. Switching one off stops it being recorded at all, so it also leaves the toolbar count, the cards and the report. Cards can be set to standouts only, standouts plus every add to cart, at most one per shop, or none. The weekly report can stop opening on its own. WORKS IN Chrome and Edge on desktop, and Firefox 140 or newer. It is free. OPEN SOURCE The full source, including the list of excluded sites and the exact rules for what counts as a standout, is public: https://github.com/viditChhajed/pensa