--- title: "Agentic commerce benchmark across all stores" source: "https://ottom.io/benchmarks/all" summary: "An AI shopping agent reached the payment step on 81% of the 468 stores Ottom scanned in the 90 days to 13 November 2026, in every category and including stores whose category could not be determined, counting stores that blocked the agent or stopped it early as not reached. Of the 436 measured at every stage, 87% reached it, and the median agentic readiness score was 97 out of 100." --- # Agentic commerce benchmark across all stores An AI shopping agent reached the payment step on 81% of the 468 stores Ottom scanned in the 90 days to 13 November 2026, in every category and including stores whose category could not be determined, counting stores that blocked the agent or stopped it early as not reached. Of the 436 measured at every stage, 87% reached it, and the median agentic readiness score was 97 out of 100. This benchmark pools every store Ottom has scanned, across all categories, including stores whose category could not be determined. Each store is counted once, whichever category it is in. Cohort: 436 stores measured at every stage, of 468 scanned. Window: 15 August 2026 to 13 November 2026. Version: v4.0.0. Methodology: bench-v7, https://ottom.io/benchmarks/methodology. A store enters Ottom’s survey only if a catalogue of at least ten products can be read from it in one request, which in practice means Shopify and WooCommerce storefronts. These figures therefore describe the storefronts Ottom can read in bulk rather than online retail as a whole. The methodology sets out what that excludes. Between 1 and 10 October 2026 the median score across all stores rose from 55 to 97. The stores did not change. Our agent did. On 4 October 2026 we replaced the scripted agent that walked checkout, agent-v1, with a new one, agent-v2, and from 8 October 2026 we measured every surveyed store again with it. On 250 stores measured by both, the old agent reached the payment step on 5 and the new one on 212. Figures before 10 October 2026 were measured wholly or partly by the old agent and are not compared with figures after it. ## Reaching the payment step An AI shopping agent reached the payment step on 81% of the 468 stores Ottom scanned in the 90 days to 13 November 2026, counting stores that blocked it or stopped it early as not reached, and on 87% of the 436 measured at every stage. Ottom stops there and never submits payment. | Of all stores scanned | Of stores measured at every stage | | --- | --- | | 81% of 468 | 87% of 436 | ## Where agents stall Of the 436 stores Ottom measured at every stage, 85% scored 80 or better at the discover stage, against 89% at the compare stage. | Stage | Median score | Stores passing | Stores measured | | --- | --- | --- | --- | | Discover | 100 | 85% | 436 | | Evaluate | 88 | 88% | 436 | | Compare | 100 | 89% | 436 | | Buy | 100 | 87% | 436 | ## What stops them The most common stall across all stores is products have no GTIN or MPN to match against, found on 63% of the 468 stores Ottom scanned in the 90 days to 13 November 2026. | Stall | Stage | Severity | Share of stores | | --- | --- | --- | --- | | Products have no GTIN or MPN to match against | Evaluate | medium | 63% | | Variants are not described in structured data | Evaluate | high | 11% | | Shipping cost cannot be determined before checkout | Compare | high | 9% | | Product pages have no schema.org markup | Discover | high | 8% | | Add to cart needs JavaScript the agent cannot run | Buy | medium | 7% | | No sitemap for agents to crawl | Discover | high | 6% | | No llms.txt to orient agents | Discover | low | 4% | | Agent could not reach the payment step | Buy | critical | 3% | | Feed price and storefront price disagree | Compare | high | 2% | | No machine-readable product feed | Discover | high | 2% | 12 further stalls were found but withheld, because too few stores showed them to report a share without pointing at an individual store. ## Readiness score The median of the 436 stores Ottom measured at every stage in the 90 days to 13 November 2026 scored 97 out of 100, and a quarter of them scored 93 or below. | Lower quartile | Median | Upper quartile | | --- | --- | --- | | 93 | 97 | 97 | Most stores score near the top: three quarters score 93 or more, and the middle store scores 97. Reaching the payment step is worth 40 of the 100 points, and a store where the agent did not reach it can earn at most 18 of those 40. So the score separates the stores an agent can buy from from the stores it cannot, and does not separate stores within each group by much. ## Can AI agents read these stores? Before an AI agent can compare or buy anything, it has to be let in and find something it can read. These figures come from the first step of every scan, across the 465 online stores Ottom scanned in the 90 days to 13 November 2026, in every category. | Check | Share | Of | | --- | --- | --- | | Block AI agents in robots.txt | Under 1% | 465 every store scanned | | Stop agents with bot protection | Under 1% | 465 stores robots.txt lets in | | No machine-readable product feed | 2% | 463 stores an agent could open | | No llms.txt | 4% | 463 stores an agent could open | | No schema.org Product markup | 8% | 456 stores whose product pages an agent read | | No shipping costs before checkout | 9% | 456 stores whose product pages an agent read | Fewer than 1% of the 465 online stores Ottom scanned in the 90 days to 13 November 2026 block AI agents in robots.txt. Of the 465 stores Ottom scanned in the 90 days to 13 November 2026 whose robots.txt lets AI agents in, fewer than 1% stop an AI agent with bot protection before the storefront loads. Of the 463 stores Ottom scanned in the 90 days to 13 November 2026 whose storefront an AI agent could open, 2% publish no machine-readable product feed. Of the 463 stores Ottom scanned in the 90 days to 13 November 2026 whose storefront an AI agent could open, 4% publish no llms.txt. Of the 456 stores Ottom scanned in the 90 days to 13 November 2026 whose product pages an AI agent could read, 8% carry no schema.org Product markup on those pages. Of the 456 stores Ottom scanned in the 90 days to 13 November 2026 whose product pages an AI agent could read, 9% give no shipping costs an agent can read before checkout. Each share is counted over the stores that reached the point where it is checked, which the sentence names. When fewer than 5 stores show something, the exact share is not given: the panel gives a bound it is under, so no store can be singled out, or withholds the figure when the stores counted are too few for that bound to be small. A store enters Ottom’s survey only if its catalogue can be read, so these are mostly stores an agent can reach, and blocking may well be more common across online retail as a whole. ### Which stores publish a UCP manifest? A Universal Commerce Protocol manifest is a file at /.well-known/ucp that tells an AI agent platform which UCP services a store offers and where to reach them. Ottom reads it once per scan and counts it here as an observation, not a score: a store without one is not marked down. The figures are split by platform because a hosted platform that supports UCP usually publishes the file for every store on it, so one pooled share would mostly measure the platform mix. Of the 162 Shopify stores Ottom scanned in the 90 days to 13 November 2026 whose UCP manifest it checked, 99% publish one at /.well-known/ucp. The same figures as JSON: https://ottom.io/benchmarks/readability.json ## How to cite this benchmark These figures are published under CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Credit Ottom and link to this page. Ottom, Agentic commerce benchmark across all stores v4.0.0, 15 August 2026 to 13 November 2026, methodology bench-v7, agent-v2. https://ottom.io/benchmarks/all. Licensed CC BY 4.0. As HTML: ```html Source: Ottom, Agentic commerce benchmark across all stores v4.0.0, 15 August 2026 to 13 November 2026, methodology bench-v7, agent-v2. Licensed under CC BY 4.0. ``` The same figures as JSON: https://ottom.io/benchmarks/all/data.json ## Previous versions - v3.0.1, issued 2026-10-27: https://ottom.io/benchmarks/all/v3.0.1 - v3.0.0, issued 2026-10-22: https://ottom.io/benchmarks/all/v3.0.0 - v2.0.12, issued 2026-10-20: https://ottom.io/benchmarks/all/v2.0.12 - v2.0.11, issued 2026-10-17: https://ottom.io/benchmarks/all/v2.0.11 - v2.0.10, issued 2026-10-16: https://ottom.io/benchmarks/all/v2.0.10 - v2.0.9, issued 2026-10-15: https://ottom.io/benchmarks/all/v2.0.9 - v2.0.8, issued 2026-10-13: https://ottom.io/benchmarks/all/v2.0.8 - v2.0.7, issued 2026-10-12: https://ottom.io/benchmarks/all/v2.0.7 - v2.0.6, issued 2026-10-10: https://ottom.io/benchmarks/all/v2.0.6 - v2.0.5, issued 2026-10-09: https://ottom.io/benchmarks/all/v2.0.5 - v2.0.4, issued 2026-10-06: https://ottom.io/benchmarks/all/v2.0.4 - v2.0.3, issued 2026-10-05: https://ottom.io/benchmarks/all/v2.0.3 - v2.0.2, issued 2026-10-01: https://ottom.io/benchmarks/all/v2.0.2 - v2.0.1, issued 2026-09-30: https://ottom.io/benchmarks/all/v2.0.1 - v2.0.0, issued 2026-09-29: https://ottom.io/benchmarks/all/v2.0.0 - v1.0.0, issued 2026-09-25: https://ottom.io/benchmarks/all/v1.0.0