Agent-Readiness Score
Crail's published, 0-100 composite score measuring how usable a piece of software is for an AI agent to discover, evaluate, and buy — not how good the product itself is.
The score averages six sub-dimensions, each also 0-100: discoverability (llms.txt, robots.txt access for AI crawlers, schema.org markup), machine-readable content (clean docs vs. JS-only rendering), programmatic access (self-serve API keys and sandboxes), MCP/agent-native support, self-serve transactability (can an agent complete a purchase without a human sales call), and transparency (public pricing and security docs). The scoring methodology is published at /methodology and versioned (current: crail-ar-v0.1) so scores are auditable rather than a black box — see the methodology page for the full breakdown.
Last verified: