Agent readiness score explained
Why one domain reads 99 at one scanner and 84 at another, and how to compare the scales.
In short
The same domain reads 99 at Ora, 100 at Is Agentic and 84 at Mintlify because each scanner prints its own scale. 5 of the 10 scanners publish thresholds, from Ora's A+ at 95 to StartupHub's A+ at 90 and Cloudflare's level 0 to 5, which is set by checks passed, not by points.
One domain, three printed scores
| Scanner | Printed score | Scale it uses | Report |
|---|---|---|---|
| 99 of 100, grade A+ | A+ is 95 to 100, labelled Leading | Report page 13 | |
| is-agentic.com | 100 of 100, Strong technical baseline | A band label; no thresholds published | Report page 10 |
| 84 of 100, grade B | B is 80 to 89 on the AFDocs scale | Report page 14 |
The reports are shown in full on the pick page. Mintlify's score page is built for documentation sites, so its number answers a different question from the other two.
The scales scanners print
| Scanner | Scale |
|---|---|
| Letter grades: A+ 95 to 100, A 86 to 94, B 70 to 85, C 48 to 69, D 28 to 47, F 0 to 27 9 | |
| is-agentic.com | A band label beside the score, for example Strong technical baseline at 100; no thresholds published 10 |
| Letter grades: the scanner page puts A+ at 90 and above, A 80, B 70, C 60, D 40 and F under 40; the spec gives D as 50 to 59 and F under 50 11 | |
| Levels 0 (Not Ready) to 5 (Agent-Native), set by which groups of checks pass rather than by a point total 5 | |
| Bands: 90 to 100 excellent, 70 to 89 good, 50 to 69 fair, 0 to 49 needs improvement 4 | |
| Letter grades on the AFDocs scale: A+ 100, A 90 to 99, B 80 to 89, C 70 to 79, D 60 to 69, F 0 to 59 12 | |
| No weighted score by design: a pass ratio and pass or fail status per audit 7 | |
| SEOJuice Agent Ready | Levels 0 to 5: 0 is 0 to 9, 1 is 10 to 24, 2 is 25 to 49, 3 is 50 to 69, 4 is 70 to 84 and 5 is 85 and above 8 |
What each number is made of
| Scanner | How the score is built | Source |
|---|---|---|
| layer points 20, 30, 40, 10 and per-check maxScore | ora.ai/methodology | |
| overall score is the simple average of six dimension scores, each the share of applicable checks passed; a warning counts 40 percent | startuphub.ai/spec | |
| is-agentic.com | Essential checks share an 80-point pool, recommended checks a 20-point pool, emerging signals a bonus capped at 5 points | is-agentic.com/methodology |
| overall score is an unweighted pass percentage; the llms.txt sub-score weights are 3x, 1x and 0.5x; the MCP scanner weights are in a table | agent-ready.dev/methodology | |
| levels are defined by check combinations and the launch post says commerce checks do not count; no per-check or per-category weights published | isitagentready.com/llms-full.txt | |
| AFDocs, the standard the score is built on, publishes weights of 10, 7, 4 and 2 points; the mint score docs say the score is weighted | afdocs.dev/agent-score-calculation.md | |
| no weighted score by design | developer.chrome.com/docs/lighthouse/agentic-browsing/scoring | |
| SEOJuice Agent Ready | category weights 20, 15, 20, 45 percent | seojuice.com/tools/agent-ready |
| none | none | |
| none | none |
Where a scanner's own pages disagree
StartupHub's scanner page puts grade D at 40 and F under 40, while its published specification gives D as 50 to 59 and F under 50 112. Cloudflare's launch post describes four scored dimensions and says commerce checks do not count, while its current documentation lists five categories and 23 checks 155. Ora's methodology page lists 126 checks and its API catalog 132 1.
Reading a score across scanners
Compare the order a scanner gives, not the number. On the sixty Concordance domains Ora's median score is 64.5 and Cloudflare's is 20, yet their rank correlation is 0.79: they order the sites alike on different scales. The edition page shows the correlations for every pair, and the guide to disagreements explains the causes.
Sources
- ora.ai/methodology. https://ora.ai/methodology, read 2026-11-05.
- startuphub.ai/spec. https://www.startuphub.ai/spec, read 2026-11-05.
- is-agentic.com/methodology. https://is-agentic.com/methodology, read 2026-11-05.
- agent-ready.dev/methodology. https://agent-ready.dev/methodology, read 2026-11-05.
- isitagentready.com/llms-full.txt. https://isitagentready.com/llms-full.txt, read 2026-11-05.
- afdocs.dev/agent-score-calculation.md. https://afdocs.dev/agent-score-calculation.md, read 2026-11-05.
- developer.chrome.com/docs/lighthouse/agentic-browsing/scoring. https://developer.chrome.com/docs/lighthouse/agentic-browsing/scoring, read 2026-11-05.
- seojuice.com/tools/agent-ready. https://seojuice.com/tools/agent-ready/, read 2026-11-05.
- ora.ai/llms-full.txt. https://ora.ai/llms-full.txt, read 2026-11-04.
- is-agentic.com/scan/telnyx.com. https://is-agentic.com/scan/telnyx.com, read 2026-11-05.
- startuphub.ai/agent-readiness. https://www.startuphub.ai/agent-readiness, read 2026-11-05.
- afdocs.dev/what-is-agent-score.md. https://afdocs.dev/what-is-agent-score.md, read 2026-11-05.
- ora.ai/score/telnyx.com. https://ora.ai/score/telnyx.com, read 2026-11-05.
- mintlify.com/score/telnyx.com. https://www.mintlify.com/score/telnyx.com, read 2026-11-05.
- blog.cloudflare.com/agent-readiness. https://blog.cloudflare.com/agent-readiness/, read 2026-11-05.
Last reviewed 2026-11-05