---
title: "How to read a readiness score | Agent Readiness Compare"
description: "A short lesson on what an agent readiness score contains: layers, points, check counts, grade bands and method dates, and what a score cannot tell you."
canonical: https://agentreadinesscompare.com/university/how-to-read-a-readiness-score/
site: "Agent Readiness Compare"
last_updated: 2026-11-05
date: 2026-09-12
section: "University"
---

# How to read a readiness score | Agent Readiness Compare

> A short lesson on what an agent readiness score contains: layers, points, check counts, grade bands and method dates, and what a score cannot tell you.

Source: https://agentreadinesscompare.com/university/how-to-read-a-readiness-score/
Site: Agent Readiness Compare
Last reviewed: 2026-11-05

# How to read an agent readiness score

What goes into the number, and what it cannot tell you.

In short

A readiness score adds up the signals a scanner found, weighted by its own rules. To read one, look at the layer breakdown before the total, check which rules produced it and when, and treat it as a map of gaps rather than a measure of outcomes. A score does not show AI visibility, traffic or revenue.

## 1. What is inside the number

A score is a weighted sum. Ora's methodology is a published example: four layers worth 20 points for Discovery, 30 for Access, 40 for Usability and 10 for Payments, normalised to 100.

| Layer | Points | Checks, methodology page | Checks, API catalog |
| --- | --- | --- | --- |
| Discovery | 20 | 16 | 16 |
| Access | 30 | 42 | 42 |
| Usability | 40 | 62 | 68 |
| Payments | 10 | 6 | 6 |

The two counts disagree by six Usability checks, 126 against 132 in total, so record which source you used. The total maps to grade bands: A+ (95 to 100, Leading), A (86 to 94, Agent-Ready), B (70 to 85, Competitive), C (48 to 69, Needs Work), D (28 to 47, At Risk) and F (0 to 27, Unusable).

Other scanners use other rules. is-agentic.com, where Ora runs the scans, uses tiers: Essential checks share 80 points, Recommended checks 20, and emerging signals add a bonus capped at 5. agent-ready.dev divides passing checks by total checks across 72 and counts warnings as failures. Cloudflare reports a level from 0 to 5 across 23 checks and publishes no weights or level thresholds.

## 2. Read the layers before the total

A total can hide a weak layer. A site with strong discovery and access can post a respectable total while scoring low on usability, which is where an agent tries to operate, authenticate and complete a task. Compare each layer's points with its maximum, then read the failing checks inside the weakest layer. That is usually the order to fix things in.

## 3. Which checks count

Scanners differ in what they include. Ora's catalog sorts its 132 checks into 29 required, 77 recommended and 26 emerging, and flags 61 as bonus. Checks that do not apply, and bonus checks a site does not earn, leave the denominator. All six payment checks are bonus checks, so a product that takes no payments is not marked down. Auth-gated APIs that return 401 or 403 are scored on documentation evidence, not runtime probes.

Two scanners can therefore grade the same site differently for defensible reasons. The [Scanner Concordance](https://agentreadinesscompare.com/concordance/) shows sixty domains scored by every public scanner on the same day. [Why scanners disagree](https://agentreadinesscompare.com/guides/why-scanners-disagree/) explains the gaps.

## 4. Why the date matters

A score moves for one of two reasons: your site changed, or the rules changed. Ora versions its catalog with SemVer and reported contract 1.38.0 on 4 November 2026. Cloudflare launched with four dimensions in April 2026 and lists five categories now. Record the date and the scanner's method with each score, so a later change can be traced to one cause or the other.

## 5. What a score cannot tell you

-   Whether an agent completed your most valuable task. A task run answers that; see [lesson 6](https://agentreadinesscompare.com/university/file-checks-and-task-runs/).
-   What happens behind sign-in. Ora does not scan private or logged-in pages.
-   How often you appear in AI answers, or whether readiness work changed sign-ups or revenue. Measure those with your own analytics.

For calibration, Ora's home page reported on 4 November 2026 that 145,204 sites were scanned, the average score was 43 and 6 percent were at B or above. Those are Ora's own figures about its own sample.

## 6. Related

-   [File checks and task runs](https://agentreadinesscompare.com/university/file-checks-and-task-runs/)
-   [How to read an Ora score](https://agentreadinesscompare.com/guides/how-to-read-an-ora-score/)
-   [How to read a Cloudflare band](https://agentreadinesscompare.com/guides/how-to-read-a-cloudflare-band/)
-   [Scanner Concordance](https://agentreadinesscompare.com/concordance/)
-   [Method](https://agentreadinesscompare.com/method/)
-   [Agent readiness score explained](https://agentreadinesscompare.com/agent-readiness-score-explained/)

## 7. Sources

1.  Ora, methodology. [https://ora.ai/methodology](https://ora.ai/methodology?utm_source=agentreadinesscompare.com&utm_medium=referral&utm_campaign=lesson), read 2026-11-04.
2.  Ora, check catalog (contract 1.38.0). [https://ora.ai/api/checks](https://ora.ai/api/checks?utm_source=agentreadinesscompare.com&utm_medium=referral&utm_campaign=lesson), read 2026-11-04.
3.  Ora, llms-full.txt. [https://ora.ai/llms-full.txt](https://ora.ai/llms-full.txt?utm_source=agentreadinesscompare.com&utm_medium=referral&utm_campaign=lesson), read 2026-11-04.
4.  Ora, home page. [https://ora.ai/](https://ora.ai/?utm_source=agentreadinesscompare.com&utm_medium=referral&utm_campaign=lesson), read 2026-11-04.
5.  Ora, is-agentic.com with Vercel. [https://ora.ai/blog/is-agentic-with-vercel](https://ora.ai/blog/is-agentic-with-vercel?utm_source=agentreadinesscompare.com&utm_medium=referral&utm_campaign=lesson), read 2026-11-04.
6.  is-agentic.com, methodology. [https://is-agentic.com/methodology](https://is-agentic.com/methodology), read 2026-11-04.
7.  agent-ready.dev, methodology. [https://agent-ready.dev/methodology](https://agent-ready.dev/methodology), read 2026-11-04.
8.  Cloudflare, isitagentready.com llms.txt. [https://isitagentready.com/llms.txt](https://isitagentready.com/llms.txt), read 2026-11-04.
9.  Cloudflare, Agent Readiness. [https://blog.cloudflare.com/agent-readiness/](https://blog.cloudflare.com/agent-readiness/), read 2026-11-04.

Last reviewed 2026-11-05
