Methodology

Is Agentic estimates how readily AI agents can discover, access, understand, and use a public website. The technical score is derived from check-level evidence supplied by Ora, then weighted by Agent Rubric according to maturity and applicability. The score is an at-a-glance summary; the individual checks and evidence are the useful part of the report.

Essential checks share an 80-point pool and recommended checks share a 20-point pool. Emerging signals can add a small bonus, capped at five points, without becoming requirements. Not-applicable checks are excluded, partial results receive proportional credit, and duplicated check IDs across MCP surfaces are averaged. API, OAuth, MCP, GraphQL, and MCP Apps checks activate only when that surface is positively identified.

Ora performs the underlying scan and returns layers, checks, evidence, and recommendations. Is Agentic applies its own applicability-aware presentation and weighting to that evidence. We also provide a prioritized implementation prompt, observed agent journeys, public share pages, caching, and historical storage.

Read Ora's API documentation and methodology for the current check definitions and scoring details.

A report shows its scan timestamp. Completed scans are cached for fast retrieval. When a score is requested, Ora may return a complete result from its six-hour freshness cache without running another scan. Agent Rubric stores the latest completed result as a static public report, while snapshots may be retained for historical comparison. A score can change because the target changed, Ora's methodology changed, or a time-sensitive check returned a different result.

“Prompt to fix” converts all actionable recommendations returned by Ora into an implementation brief. The estimated gain, when present, is directional rather than guaranteed. Review evidence in context, implement changes safely, and rescan to verify the outcome.

• Scans observe public behavior at a point in time.
• Automated checks can produce false positives, false negatives, or partial results.
• A high score is not a security, accessibility, quality, compliance, or compatibility certification.
• A score does not imply affiliation with or endorsement of the scanned site.