# AgentReady Monitor

> What do AI models recommend when buyers ask about your category?

AgentReady Monitor measures every month what ChatGPT, Claude, Perplexity and Gemini answer when potential buyers ask about your category. Score, share of answer, competitor tracking and alerts — for companies that want to know whether they show up in AI answers at all.

## What you get

- **Score 0–100**: One value per model and one overall, built from visibility, accuracy and sentiment. Trend chart across every month measured.
- **Share of answer**: The share of comparison questions where you are named — next to every competitor. "Craftnote is recommended in 80% of comparisons, you in 40%."
- **Answer matrix**: Every single answer verbatim, sorted by prompt and model, with its score and reasoning. Filterable by block and language.
- **Gaps**: What the models could not answer about you — deduplicated and ranked. That is your FAQ backlog for the next few weeks.
- **Alerts**: Email when the score drops by more than 10 points or a competitor newly enters the recommendations. Pro plan.
- **API instead of click paths**: Everything the dashboard does, the API does too. Bearer tokens, an OpenAPI spec, one endpoint per job — built for agents that ask on their own.

## Pricing

- Trial: free, 14 days · Starter: 49 EUR/month · Pro: 149 EUR/month
- Trial: 1 case(s), 2 models, languages en
- Starter: 1 case(s), 4 models, languages en/de
- Pro: 3 case(s), 9 models, languages en/de, alerts, manual re-runs

## Pages

- [Home](https://ai-agent-ready.com/index.md): product, process, pricing, FAQ
- [Pricing](https://ai-agent-ready.com/pricing.md): plans in detail
- [FAQ](https://ai-agent-ready.com/faq.md): common questions
- [Fix](https://ai-agent-ready.com/fix.md): the sister product that repairs the technical findings
- [Blog](https://ai-agent-ready.com/blog.md): guides, data and definitions
- [API docs](https://ai-agent-ready.com/docs/api.md): endpoints, auth, examples
- [Check](https://ai-agent-ready.com/check.md): the free technical scanner
- [Report](https://ai-agent-ready.com/report.md): live market data from every scan

## Guides

- [Bot traffic passed human traffic 18 months ahead of forecast](https://ai-agent-ready.com/blog/bot-traffic-passed-human-traffic.md): Cloudflare predicted the crossover for late 2027, then revised it to early 2027. It had already happened in the first half of 2026. What a forecast wrong twice in the same direction means for anyone still planning to deal with this next year.
- [A brand is a shortcut. Agents don't take shortcuts.](https://ai-agent-ready.com/blog/brand-in-an-agentic-world.md): Brands exist because humans have limited patience for evaluating options. Agents have effectively unlimited patience — which changes what you have to publish in order to get recommended.
- [How to allow GPTBot and other AI crawlers in robots.txt](https://ai-agent-ready.com/blog/fix-ai-crawlers-blocked.md): The exact robots.txt block for GPTBot, OAI-SearchBot, ClaudeBot, PerplexityBot and Google-Extended — plus the reason robots.txt alone is often not enough.
- [Why AI crawlers cannot read your JavaScript site](https://ai-agent-ready.com/blog/fix-js-rendering.md): AI crawlers do not execute JavaScript. What that means for client-rendered apps, how to check what they actually see, and what to fix first.
- [What is llms.txt, and is it worth adding?](https://ai-agent-ready.com/blog/fix-no-llms-txt.md): A plain explanation of the llms.txt proposal: what belongs in the file, how it differs from robots.txt and sitemap.xml, and the honest state of adoption.
- [Every byte of your HTML competes for the same context window](https://ai-agent-ready.com/blog/html-cruft-and-context-windows.md): Cloudflare strips pages down to Markdown before handing them to AI systems, so more of the content fits in a model's context. What that implies for how you publish.

## Check — technical agent readiness

- [AgentReady Check](https://ai-agent-ready.com/check): The 3-minute check: 9 areas, 100 points, your agent-readiness score. Free, no login. Markdown: https://ai-agent-ready.com/check.md
- [How it works](https://ai-agent-ready.com/check/how-it-works): all 9 checks and the scoring logic. Markdown: https://ai-agent-ready.com/check/how-it-works.md
- Scanned domains so far: 21.
- Pillars: Retrievable (51 points), Explainable (37 points), Actionable (7 points), Distributed (5 points).
- 3 of 9 checks are visible immediately, the remaining 6 after entering an email address. The API always returns all 9.
- The score is a percentage of the applicable points, not a plain sum: areas that do not apply to a domain (a blog has no checkout) are removed from the calculation, and signals that cannot be verified from outside count as half rather than zero. A check can therefore report state "unknown" with max 0.

## API

- Base URL: https://ai-agent-ready.com/api/v1
- OpenAPI: https://ai-agent-ready.com/api/v1/openapi.json
- Agent manifest: https://ai-agent-ready.com/.well-known/ai-plugin.json — points at the same OpenAPI, no auth, free.
- Auth: `Authorization: Bearer <api-key>`
- Everything the dashboard does, the API does too.
- Every response carries `meta.pricing` (currently `{"model":"free"}`) — ready for agent payments over HTTP 402.

## MCP v0 (in-app)

- An MCP server runs at `/api/mcp` (Authorization header) and `/api/mcp/{api_key}` (key in the path, for clients without header support).
- This is v0: it runs inside the Next.js app and calls the data layer directly. Planned to move to a standalone Cloudflare Worker in front of `/api/v1` — URL and tool names stay the same.
- Case tools (read-only): `list_cases`, `get_case`, `list_runs`, `get_case_summary`.
- Check tools: `scan_domain` (blocks 5-30s while it fetches the live site), `get_scan`, `get_stats`.
- Each maps 1:1 to a REST endpoint; the tool name is the OpenAPI operationId.
- Scope: a key reads its own cases. Keys carrying the `monitor:admin` scope read every tenant.

## More from The Autopilot

- [The 21-Process Check](https://check.the-autopilot.com): How much of your business already runs without you? (German)
- [Clapr](https://www.clapr.io): Run your YouTube pipeline on autopilot with AI agents.
- [Loop Engineer](https://www.loop-engineer.de): Learn loop engineering in eight missions. (German)

## Optional

- [Full text](https://ai-agent-ready.com/llms-full.txt): every landing page as Markdown