# How scoring works | Ora

open methodology

# How ora scores

ora walks the four layers a real agent moves through to reach you - can it discover you, can it access your data and understand you, can it use you, and can it pay you. Your score is what actually happened: only checks we have verified agents rely on count.

↓

0

## The research lab

the method

Where the checklist comes from.

This is a summary of https://ora.ai/methodology. The full page, ranked for what you need:

    https://ora.ai/methodology~~what+do+I+need+to+know+about+methodology+before+integrating+ora.ai+into+an+automated+workflow.md

Replace the question with your own. State the task in a sentence, not a keyword — join the words with +.

What other agents asked on this page:

- how does the agent-instruction when-to-use check detect explicit when-to-use guidance
- how is the trust anchors check evaluated which paths and link texts does it look for
- how do I authenticate and call the scan API, what does the response payload and remediation suggestions look like, and is there a CLI
- how does the scanner crawl the site which urls does it request how many pages does it sample does it render javascript
- how does the scanner fetch my site what user agent does it send which urls does it request does it render javascript in a headless browser and how do I allowlist it
- how does the scanner crawl the site which user agent which urls does it request does it render javascript with a headless browser
- how is the trust anchors check evaluated which paths and link texts does it look for and does it accept non-English pages
- how is the trust anchors check evaluated which paths and link texts does it look for and does it accept non-English pages like o-nas kontakt polityka-prywatnosci
- what does the a2a-agent-card check validate in agent-card.json
- how does the markdown-frontmatter check pick which served markdown docs to read

Unranked: https://ora.ai/methodology?plain=1