Agent-readiness report, Beauty and personal care
No class of agent can use Blume today: they cannot call it as a tool.
blume.com, Shopify, last scanned yesterday, on 29.09.2026
Agent classes working
0/3
Score history
▼ 34 scans since 21.09.2026
0 of 3 agent classes work
Tool-calling assistants have no function to call, so they can only scrape.
BlockerWhen something breaks, an agent operator has no documented way to reach you.
ImprovementA model cannot tell that this domain is the brand it was asked about.
ImprovementCautious platforms will not act on the site without an explicit permission signal.
ImprovementPlatforms cannot tell whether AI training, AI answers or search use is permitted.
ImprovementFree dashboard
Weekly re-scans, the fix for every gap above, and the rank moves of your rivals.
Your dashboard
We email you a sign-in link and add blume.com to your dashboard.
Online retailer specializing in clean, affordable, and effective skincare products for a conscious consumer base, predominantly in North America.
We asked Gemini
“A buyer asks: which companies would you recommend for Online retailer specializing in clean, affordable, and effective skincare products for a conscious consumer base, predominantly in North America. in Primarily North America (United States and Canada), though as an online retailer, it may ship to other regions.? Answer as you normally would and name the companies you would suggest, with their websites.”
"For an online retailer specializing in clean, affordable, and effective skincare for a conscious North American consumer base, I would strongly recommend exploring models similar to The Ordinary at deciem.com, Good Molecules at goodmolecules.com, and cocokind at cocokind.com. These brands successfully balance efficacy…
✕Not visible| Website | Gemini | ChatGPT Unlocked with AI monitor | Perplexity | Copilot | Other |
|---|---|---|---|---|---|
| blume.com | ✕Not visible | ||||
| ✕Not visible | |||||
| ✕Not visible | |||||
| ✕Not visible |
Approximate assistant usage share · StatCounter · Gemini also answers inside Google Search (AI Overviews, 2B+ monthly users).
5 domains free, unlimited with a plan.
Blume exposes 4 of 8 interfaces agents look for: AI crawler access, Bot user-agent handling, Server-rendered content, llms.txt.
Locked
All 8 interfaces and 26 checks for blume.com
See which interface is missing, what each check looked for, and what to change to pass it. Free account, no card.
View detailed signalsMeasured separately, not part of the public score or rank
Add-on score
37/100
Agents cannot tell what is for sale, so the catalogue is invisible to them.
Comparison agents quote a stale price or leave the shop out of the comparison.
Agents using Qomvia cannot get an agent price or a payable order from this shop.
Agents cannot match your product to the same product elsewhere, so it drops out of comparisons.
The seal
Agents can read the site, but acting on it still breaks. Paste this line where you want the seal: it is drawn at runtime, so it upgrades itself when you improve and removes itself if a deploy closes the site to agents.
<script src="https://qomvia.com/badge.js" data-slug="blume-com" async></script>There is no image URL and no static version. The seal exists only as markup we serve per request, which is what makes it worth displaying.
Blume (blume.com) scores 70 out of 100 for agent readiness, grade C, measured yesterday, on 29.09.2026. 0 of 3 agent classes we test can use the site, and 1 check currently block agents outright.
The heaviest problems are: No MCP endpoint to call; No machine-readable contact; Organisation structured data; Stated automated-access policy; No Content Signals. Each one is scored from a public HTTP response, and the fix for each is listed in the signed-in report.
Qomvia fetches public pages of blume.com as an AI agent would and runs the core checks every site gets across 6 groups: Machine access, Content legibility, Discovery surface, Identity & policy, Agent-facing performance, Agent protocols. Checks are weighted by how much an agent loses when they fail, and the score is expressed out of 100. E-commerce & product feeds checks are scored separately (37/100) and do not affect the public score or rank.
Public scores are re-checked when the site is re-scanned; tracked domains are re-scanned weekly and their owners are alerted when a check regresses. This page shows the scan from yesterday, on 29.09.2026.
Scores are computed from public HTTP responses only. We never submit forms, never attempt a purchase and never bypass a bot challenge. Disagree with a result? Request a correction or opt this domain out.