A bot grades whether a shopping agent can actually buy from a store — its creator says Amazon scored a D. Every online shop is a fixed-price audit client
Brian Roemmele built a free bot that checks, as an honest machine, whether a shopping agent can load, price and check out at any store. He says Amazon scored a D, 37 out of 100 (reported). Small shops are the audit market.
Published Nov 7, 2026
Free check · public files only
Is your store or SaaS agent-ready?
Paste a public homepage. We read a few public files — robots.txt, llms.txt, markup, and whether a pricing page or agent endpoint is in the open — and show a short score right away. The full report unlocks when you leave an email. That signup is the same newsletter as everywhere else on this site: we email a confirmation link, and you confirm on our site.
0 passed · 0 warnings · 0 failed
See the full report
Enter your email to unlock the check-by-check report and a matching Build This Business page. We only send the standard confirmation email.
Free. Double opt-in: we email you a link; tap it, then tap Confirm on our site. Unsubscribe any time. Privacy.
Full report
This is a snapshot of public files, not a certification, a rank, or a prediction of sales. We do not log in, submit forms, call any tool on an MCP server, or store the page content. Results can be cached for 24 hours per domain.
The Wow
What someone built
The Agent-Readiness Auditor scores access, catalog, total price, policy and checkout at 20 points each, then returns an A to D grade, a fix per problem, a badge and a PDF. We opened the bot page on Nov 7, 2026.
- Original source
- Agent-Readiness Auditor (Grok Bot)
- License
- Free to use as published by its creator; quote and link. Build your own audit service and checklist rather than reselling his bot
- What you need
- A public store URL
- Access to the Grok Bot link
- A store owner's permission before you publish or share their grade
- Install
- Open the bot link, paste a public store URL, and read the graded report.
- A business you could build on it
- Fixed-price agent-commerce audit and fix sprint for small stores
Why it's remarkable
It never logs in, orders, solves a captcha or poses as a person. The fixes are concrete: product data in JSON-LD, a numeric return window, shipping and tax in data, agent-friendly access rules and a Universal Commerce Protocol profile.
The Opportunity
The business it reveals
Stores already pay for SEO and conversion audits. An agent-commerce audit plus a fix sprint is the same purchase for the next kind of shopper.
Who would pay
Shopify and WooCommerce store owners first, then e-commerce agencies reselling the report.
The Flip
3 ways you could turn this into a business
Fixed-price agent-commerce audit and fix sprint for small stores
- Who pays
- Shopify and WooCommerce store owners
- How it would earn
- A fixed audit fee, then a separate fee to ship the structured data, policy and protocol fixes (our hypothesis)
- Why it might work
- The checklist and fixes are concrete, the badge gives owners something to show, and stores already buy SEO audits.
- What already exists
- SEO and conversion agencies that do not test agent checkout; waiting for the platform to add it.
White-label readiness reports for e-commerce agencies
- Who pays
- Small e-commerce and SEO agencies
- How it would earn
- A per-report or monthly fee for branded agent-readiness reports they resell to clients (our hypothesis)
- Why it might work
- Agencies need a new deliverable as agent shopping grows, and one operator can serve many agencies.
- What already exists
- Agencies building their own checklist; generic site-audit software.
Monthly agent-shelf monitor for a niche
- Who pays
- Stores in one category, such as specialty food, outdoor gear or beauty
- How it would earn
- A small monthly fee to re-test the store and its top rivals and flag when an agent can no longer buy (our hypothesis)
- Why it might work
- Grades change as themes, apps and firewalls change; a niche benchmark gives owners a reason to keep paying.
- What already exists
- One-time audits; uptime monitors that never check catalog or checkout data.
Why we'd try "Fixed-price agent-commerce audit and fix sprint for small stores" first: The audit is the door opener and the fixes are paid work owners understand, with a free tool to start and no inventory or software to build.
Build It
How you could build it
A repeatable audit service: a dated five-part report (access, catalog, total price, policy, checkout), a fix list mapped to the store's platform, and a fix sprint that ships the structured data, policies and protocol profile.
First step: Run the auditor on three stores you buy from, note their grades and the top fix for each, then offer the owner of the lowest-scoring one a free walkthrough of the report.
Agents and tools
- Agent-Readiness Auditor (Grok Bot)
- ChatGPT, Claude, Gemini or Grok Bot for checks and report drafting
- Google Rich Results Test
- ucp.dev for the Universal Commerce Protocol profile
Setup
- Run the auditor on ten stores in one niche and save the dated reports.
- Turn the five sections into your own one-page report template with platform-specific fixes.
- Write a short fix playbook for Shopify and WooCommerce: Product and Offer JSON-LD, return window, shipping and tax data, agent access rules, llms.txt, UCP profile.
- Offer three free audits to owners, then price the fix sprint.
- Re-test after fixes and show the before and after grade.
What the agent does
- Loads public pages and scores the five areas
- Drafts the report and fix list
- Drafts structured-data snippets for the owner to review
What you do
- Finds stores and sells the audit
- Reviews every report before it is sent
- Implements fixes with the owner's permission and re-tests
Your first customer: A store owner you already know or buy from, offered a free audit and badge in exchange for a paid fix sprint if the grade is below B.
Test demand first: Audit ten stores in one niche this week and send each owner their private report with a fix-sprint offer. Success: two owners reply asking about the fixes.
Your starter instructions
Paste this into the AI agent you use (ChatGPT, Claude, Gemini, Grok Bot or another) as your first message. Copying it starts work in your own agent; it doesn't create or deploy a business by itself.
Running it
What stays human: Finding stores, running and reviewing each audit, explaining the grade, implementing fixes in the store's theme and apps, and re-testing after changes.
- Startup cost (estimate)
- Under $25 to start (estimate) (Estimate: the auditor is free to use, schema testing tools are free, and you need an AI plan you may already pay for)
- Running cost
- Near zero per audit beyond your time; fix work is billed hours (estimate) (Estimate: each audit is a few public page loads and a report; hours unmeasured)
- How much the agent runs
- Agents run one core part; people run the rest.
Pricing your own version? Use the free startup-cost worksheet.
The evidence
What the source shows: Roemmele's X post (Nov 6, 2026) describing the method and his Amazon test, the live bot page, the public UCP spec at ucp.dev, and a 404 at amazon.com/.well-known/ucp on our own request — checked Nov 7, 2026. No revenue is claimed.
What's ours: The audit service, agency white-label and niche monitor flips are our applications.
Worth planning around
- The Amazon grade is Roemmele's single reported test; we did not re-run his full audit.
- Shopping-agent traffic to small stores is still hard to measure.
- Nothing here shows stores paying for agent-readiness audits yet.
Sources
- Brian Roemmele on X: Is your store Grok Bot ready? (Nov 6, 2026)
- Agent-Readiness Auditor bot page (opened Nov 7, 2026)
- Universal Commerce Protocol specification (checked Nov 7, 2026)
Sources reopened Nov 7, 2026. Spot a mistake? Tell us and we'll correct it in public.
Keep reading
- How much of the work do AI agents actually run? (guide)
- He still can't write code. His five-person ad agency now runs on about 270 tools he built with Claude. Every owner-run firm needs its first five
- A marketer who doesn't code built an elk-call coaching app with Claude Code and says it hit a $650K run rate in 110 days. Every skill learned by sound is the same opening
- A free n8n workflow flags fake supplier invoices before anyone pays them — and Germany's e-invoice switch makes it a service bookkeepers can sell
- Marc Lou's agent chased a broken-shoe refund through three support desks and got his 850 AED back. Small stores now need a claims desk that can answer agents
- Every discovery and launch plan