--- title: "Where agents drop the cart, from cart to checkout" description: "Shopping agents are getting better at finding products; the losses tend to happen between the cart and checkout." source_url: "https://specoria.com/insights/where-agents-drop-the-cart/" lang: "en" --- [Insights](https://specoria.com/insights/) Field notes # Where agents drop the cart: the last few steps from cart to checkout Shopping agents are getting better at finding products; the losses tend to happen between the cart and checkout. Three sticking points from our field study, how the agent simulator marks the cart and account items, and what to fix first. By [Specoria Team](https://specoria.com/about/) October 13, 2026 4 min read ![A paper shopping cart, a plaster hand, a stone archway, torn receipts, a key and plaster fragments are arranged on cream paper, with one violet paper strip linking the cart to the archway.](https://specoria.com/insights/img/where-agents-drop-the-cart-1-64ddd5c0.jpg) The path from cart to checkout is a doorway, and not every visitor can find the handle. Illustration: Specoria · generated with AI In this article - [Three sticking points from the field study](https://specoria.com/insights/where-agents-drop-the-cart/#three-sticking-points-from-the-field-study) - [How the simulator marks the cart section](https://specoria.com/insights/where-agents-drop-the-cart/#how-the-simulator-marks-the-cart-section) - [What to fix first](https://specoria.com/insights/where-agents-drop-the-cart/#what-to-fix-first) The conversation about shopping agents usually starts with discovery: does the agent find the product, does it pick the right variant? In our field study that part was rarely the problem. The losses came later: after the product was in the cart, in the last few clicks before checkout. ## Three sticking points from the field study On 7 October 2026 we sent AI agents shopping in a real browser 40 times across five live stores. On the nine tasks that could be completed, the two strongest models reached checkout on 9 of 9; the two lighter models on 7 of 9. In other words, the lighter models failed to reach checkout in 22% of the tasks (2 of 9). It's a small sample; read it as a field observation, not a success rate ([the full field study](https://specoria.com/insights/ai-agents-shopping-in-a-real-browser/)). Three places where agents got stuck between the cart and checkout: - **A checkout button you can see but the agent can't read.** On one store, the "Go to checkout" button in the cart drawer sat inside a third-party component built with a closed shadow DOM. The button was on screen, but it never appeared among the elements the agents could act on. Agents only reached checkout by guessing the URL. - **A cart URL the agent has to guess.** On a store where the cart link was hard to find, some agents tried to guess the cart address and landed on not-found pages. - **Sign in or continue as a guest.** Agents reached this screen and the run ended there. Without a guest option, an agent acting for a user would have to stop: it can't create an account or sign in on the user's behalf. What the three have in common: none of them would stop a human shopper. A person sees the button and clicks it, spots the cart icon, notices the "guest" link on the sign-in screen. An agent can only use what the page offers it. ## How the simulator marks the cart section ![A plaster hand reaches toward a blank paper button behind a frosted glass pane, with a torn envelope, a blank card and one violet paper key on the table.](https://specoria.com/insights/img/where-agents-drop-the-cart-2-63037276.jpg) A button in plain view means little if the agent cannot reach it. Illustration: Specoria · generated with AI After each run, the agent simulator produces a 33-item friction checklist. The "Cart & account" section has five items: forced sign-up, a surprise login wall, pre-ticked boxes, items added to the cart automatically, and cart timers. These items are marked from the run log by rules, without an AI model. On e-commerce sites each item gets one of four states: - **Detected:** the friction was flagged in this run, with evidence and the step where it happened. - **Clear:** the agent reached that page, we looked, and the friction wasn't there. - **Unreached:** the agent never got to that page, so this run couldn't check it. That does not mean "clear". - **Expert:** an item a live run can't see; an expert checks it. Payment and post-order items are not measured automatically by design, because the agent stops at checkout: we never place orders, pay or enter personal data. Those items open an expert task. The "unreached" state matters most in the cart section. The forced sign-up item, for example, can only be checked once the agent reaches checkout or the "sign in or continue as a guest" screen; items added automatically only once the agent adds a product and opens the cart. If the agent didn't get that far, these items show as "unreached" and the real problem sits one step earlier (choosing a variant or adding to cart, for instance). Fixing that item first lets the next run actually check the cart items. ## What to fix first - **Keep the link to checkout on the page itself.** Even if a third-party cart component shows its own button, keep a standard link or button on the page that an agent can read. - **Make cart and checkout URLs predictable.** Have a crawlable cart link in the main navigation; send common cart and checkout URLs to a meaningful page instead of a not-found page. - **Make guest checkout as visible as the sign-in button.** Forced sign-up is where the agent's journey ends. - **Don't add items to the cart on your own, and don't pre-tick boxes.** The agent has to notice and remove them, or it misses them and takes a wrong cart back to its user. - **Hold the cart for as long as the agent needs to ask its user.** A cart that expires while waiting for approval means starting over. Most of these also make life easier for human customers. The difference: a person works around the friction and carries on; an agent hits the same friction and goes to another store. The [agent simulator](https://specoria.com/agent-simulator/) shows step by step how these last few steps go on your store. ## Related - [We sent AI agents shopping in a real browser 40 times. Here's where they got stuck.](https://specoria.com/insights/ai-agents-shopping-in-a-real-browser/) - [A bot policy by page type: what to open to AI agents and what to keep closed](https://specoria.com/insights/bot-policy-by-page-type/) - [Layers before protocols: why ACP and UCP only pay off when your product data is right](https://specoria.com/insights/layers-before-protocols-acp-ucp-product-data/) - [Trust center](https://specoria.com/trust/) What we read, what we store, sub-processors and AI use - [Agentic commerce statistics](https://specoria.com/agentic-commerce-statistics/) Sourced, dated figures you can cite FREE TEST ## Is your store ready for shopping agents? See in seconds how a shopping agent reads your store: free, instant, no email needed. The free test runs in your browser and needs JavaScript. [Request the free deep audit by email instead →](https://specoria.com/#contact) Your result opens on its own page. Want the full picture? The free deep audit and panel come next, by email.