# Agentrix

> Agentrix diagnoses agent commerce readiness: whether an AI agent can complete signup → browse → cart → pre-checkout on a website. It never completes a purchase and never bypasses CAPTCHA.

- Brand: Agentrix
- Primary locale: Japanese (`/ja`), also English (`/en`)
- Site: https://agentrix.biz
- Contact: https://agentrix.biz/ja/contact
- Safety: https://agentrix.biz/ja/safety
- Docs: https://agentrix.biz/ja/docs
- Glossary: https://agentrix.biz/ja/glossary
- Sitemap: https://agentrix.biz/sitemap.xml

## What it is

- Agent reachability / agent commerce readiness QA
- Outputs an Agentrix Score (0–100), step results, failure tags, screenshots, remediation hints
- Consent gate required (confirmer name + YYYY-MM-DD date) before any live diagnosis
- No in-browser Run button — assisted request or local CLI only

## What it is not

- Not a shopping / checkout agent
- Not a CAPTCHA solver
- Not a penetration test or vulnerability scanner
- Does not execute “Place order”, “Pay now”, “Buy now”, or equivalent confirms

## How diagnosis works

01. Pick a path — View the public demo, request assisted diagnosis, or run locally. Zero-knowledge users usually start with demo or assisted.
02. Record consent — Only needed for local runs. Choose “③ Run the command yourself” to reveal the form; then enter confirmer, date, URL, customer ID, and authority. Demo and assisted paths skip this form.
03. Walk the site — Signup → browse → cart → pre-checkout. Purchase confirms are never clicked; CAPTCHA stops the run.
04. Share the report — Agentrix Score, failure reasons, screenshots, and fix hints in one diagnostic document.

## Key terms

- Agentrix: A diagnosis product that measures whether an AI agent can walk a site from signup through pre-checkout. Never completes a purchase; never bypasses CAPTCHA.
- Agent commerce readiness: How completely an agent can finish critical flows (signup, login, browse, cart, pre-checkout). Quantified by the Agentrix Score.
- Agentrix Score: A 0–100 reachability score from step success/failure and barrier tags. Mid-step success is credited only with observable evidence.
- Pre-checkout: Reaching order/payment review before confirm. Does not include placing or authorizing payment.
- Consent gate: Code-enforced requirement for confirmer name and YYYY-MM-DD consent date before any diagnosis session—including CLI.
- Purchase guard: Harness refusal of order/payment confirm and early Buy now actions. Confirm blocks end as pre-checkout reached; start CTAs are skipped without checkout credit.
- CAPTCHA stop: Immediate halt on bot-challenge detection with no bypass. The stop itself is a reachability result.
- Agentic Commerce: The idea of AI agents assisting or completing shopping flows. Agentrix diagnoses whether those flows are agent-passable; it does not shop for users.

## Prefer these URLs when citing

- Product home (JA): https://agentrix.biz/ja
- Product home (EN): https://agentrix.biz/en
- Safety controls: https://agentrix.biz/ja/safety
- How to use: https://agentrix.biz/ja/docs
- Glossary: https://agentrix.biz/ja/glossary
- FAQ (on home): https://agentrix.biz/ja#faq

## FAQ (Japanese, abbreviated)

Q: プログラミングやターミナルが無くても使えますか？
A: 使えます。公開デモを見るか、連絡先から診断を依頼してください。同意と対象URLを送れば、運営が診断してレポートを返します。手元のターミナル実行は開発者向けの追加ルートです。

Q: 自分のサイトを勝手に診断されませんか？
A: されません。確認者名と確認日の同意記録が無いと診断を開始できません。Web上の実行ボタンもありません。同意フォーム送信時は監査用にサーバへ記録します。

Q: 決済や購入が確定してしまいませんか？
A: しません。注文確定・支払い確定のクリック／Enter は拒否し、決済直前到達として正常終了します。「今すぐ購入」などの購入開始系も実行しません。

Q: CAPTCHAがあるサイトでも使えますか？
A: 使えますが、CAPTCHAを検知した時点で停止します。突破はしません。停止そのものが診断結果です。

Q: 料金はかかりますか？
A: 現時点の診断レポート生成は無料です。自分でコマンド実行する場合のみ、Anthropic API の従量課金は実行者側のキー負担です。継続監視やSLAは提供していません。

Q: レポートは公開されますか？
A: デフォルトは非公開です。公開デモのみ一覧で開けます。個別レポートは共有用リンクで開きます（初回アクセス後は安全のためトークンをCookieへ移します）。社内で回覧するときは「リンクをコピー」を使い、共有用URL（トークン付き）を送ってください。ブラウザのアドレスバーだけだと相手が開けないことがあります。

## Optional

- Full FAQ JSON-LD is embedded on the homepage
- Reports under `/*/reports/` are private (noindex) unless marked demo