Run the free check below. It takes a few seconds.
Based on ARC's automated checks, not a live agent session. How we check
Can AI agents find your products? Not tested yet.
Not tested yet.
Can they read prices and stock? Not tested yet.
Not tested yet.
Can they get to checkout? Not tested yet.
We haven't tested checkout on this store yet.
We haven't tested checkout on this store yet.
Public files only. No login and no purchase.
Not recorded yet
This is a public file check. It does not mean an agent can buy here. Not found means those files were absent. Not confirmed means ARC could not tell. A missing or unconfirmed result is not a mark against the store.
Not recorded yet. That is not a mark against the store.
Read during the checkout check. ARC stops before payment and does not create an account.
Not recorded yet. ARC reads the page it already opened. It does not type a name, email, or phone number, and it does not submit a signup form.
Not confirmed, and a missing check, are not a mark against the store.
Same measured facts for every assistant. ARC does not test the assistant. Muse is Meta's personal agent, powered by its Muse Wonder models.
No check date is stored yet. A missing line is not a mark against the store.
Can ChatGPT buy from a store? → · Gemini, Muse and other assistants → · Check another store →
ASK YOUR AGENT
Check bricoware.it with ARC's free MCP: https://www.arcreport.ai/api/mcpFree and read-only. The line asks for a saved, dated check. It does not start a new scan.
Install the MCP →Put this free badge on your site. It shows the latest saved result, links back here, and updates after each new check. It says “ARC checkout check passed” only when a measured catalog check returned a checkout link. That is not a completed purchase, and not a live session of a named shopping agent.
Is this your store? Claim this page to add a note. Claims never change our results.
Each line is labelled by who produced it. A line that says not recorded is left out of any score.
Agent-reported
Not recorded. This is not a mark against the store.
ARC-tested (up to payment)
Not recorded. This is not a mark against the store.
Verified purchase
Not recorded. This is not a mark against the store.
The raw results behind the answer above, for developers.
Agent Reachability Matrix
Existing ARC evidence shows discovery rails, checkout paths, and known block risks. A detected rail is not a promise that a named agent can use it.
Measured: ARC probe or browser cart test · Inferred: possible surface path · Unknown: no conclusion · Public report: external source.
ARC persona (alias id muse) · shared rails + ARC browser cart test
Not confirmed
Not confirmed
Not confirmed
Watching for PAP v0.1; identity and permission rails not confirmed.
ARC persona (alias id instinct) · shared rails + ARC browser cart test
Not confirmed
Not confirmed
Not confirmed
Watching for PAP v0.1; identity and permission rails not confirmed.
ARC persona (alias id grok) · shared rails + ARC browser cart test
Not confirmed
Not confirmed
Not confirmed
Watching for PAP v0.1; identity and permission rails not confirmed.
ARC persona (alias id openai-dots) · shared rails + ARC browser cart test
Not confirmed
Not confirmed
Not confirmed
Watching for PAP v0.1; identity and permission rails not confirmed.
ARC persona (alias id openclaw) · shared rails + ARC browser cart test
Not confirmed
Not confirmed
Not confirmed
Watching for PAP v0.1; identity and permission rails not confirmed.
Universal Commerce Protocol surface · eligibility unconfirmed
Not confirmed
Google surface eligibility not tested.
Not confirmed
Not confirmed
Watching for PAP v0.1; identity and permission rails not confirmed.
Measured means an ARC HTTP rail check or an Index browser cart test, not a live Muse, Instinct, ChatGPT, Gemini, Grok, or OpenClaw session. Checkout handoff is not a completed purchase. ARC is independent and not affiliated with Meta, Sierra, Shopify, OpenAI, or Google. PAP support is not confirmed.
Real HTTP agent-catalog check. Does not change the Index score.
Public checks not fully measured
Not measured items need a successful re-check before readiness can be established.
native_commerce(checkout_eligibility): Can't be checked from outside — set in your Merchant Center feed
These are the public parts of Google's checklist that ARC can check from outside. This is not Google approval or certification. See Google's Merchant Center help on UCP / agentic checkout.
Platform: measured on the next check.
From the product page's JSON-LD, or the store's public products.json when that page has none.
Measured on the next check.
From the store's pages and structured data. Presence does not verify the policy's terms.
Measured on the next check.
PAP (announced 6 Oct 2026 by Meta and Sierra with industry partners at Genesys, Instinct, Rocket, Shopify, Stripe, and Walmart; Draft 0.1 (spec updated 12 Oct 2026)) is an open standard for how personal agents discover and work with businesses — website discovery, OAuth session, then site / APIs (MCP, OpenAPI) / company agent. Companies publish /.well-known/poppy.json. ARC already answers the two-lane question: can agents discover you, and can they buy from you. The store-hub watch probes candidate discovery paths, including /.well-known/poppy.json, and labels unknown clearly. ARC is not affiliated with Meta or Sierra.
Watching for PAP v0.1
bricoware.it is not in ARC's directory and has no stored rails check, so this page does not queue a probe.
Not a claim of PAP support. Draft 0.1 (spec updated 12 Oct 2026). This watch requests /.well-known/poppy.json and other candidate paths. It does not test conformance to that draft. Related surfaces below (UCP, WebMCP, MCP well-known) are existing agent-discovery checks.
Not probed yet · source announcement: sierra.ai/blog/introducing-personal-agent-protocol
Browser cart attempts. Score is this lane only.
Not on the curated Index yet. You can still run a free product scan.
Typed decisions over an HTTP product scrape. Not a live personal-agent session.
No Jev facts stored yet for this host.
Quoted mismatches only, from one AI model’s read-back (currently Grok via API). One model, not a consensus.
No real Grok fact check stored for this store yet.
From stored ARC rows only.
Nothing stored yet. Run a free checkout check or free score to start the timeline.
Claims never change ARC’s measured scores.
What Grok tells shoppers is a real model call via API, checked against the store's pages, not the consumer Grok app. Whether agents reach checkout is two lanes: a real HTTP check of the store's agent catalog, and five ARC browser cart tests. Those attempts are not a live Muse, Instinct, Grok Bot, OpenAI dots, or OpenClaw session. The score is the browser lane. The catalog check does not change it.