--- url: https://ora.ai/blog title: "Blog: agent readiness research and case studies" description: "What we are learning from scanning the web for agent-readiness." crawled_at: 2026-10-18T19:27:03Z ask: https://ora-ai.ora.run/ask docs: https://ora-ai.ora.run/.well-known/ora/docs lang: en --- ora // blog # How ready is the web for agents? What we're learning from scanning thousands of products for how well AI agents can find, understand, and use them. ## [AX is the new AEO](https://ora.ai/blog/ax-is-the-new-aeo) Being surfaced is not enough. We ran a controlled experiment across ~38,000 agent runs and 1,000+ businesses to measure the effect of AX on recommendation, grounding, accuracy, and cost. Oct 8, 2026 · 12 min read · Read → Research paper ## [When a WebMCP tool returns an MCP App](https://ora.ai/blog/when-a-webmcp-tool-returns-an-mcp-app) WebMCP lets a website hand tools to the agent. MCP Apps lets a server hand UI to the human. We built an experiment where one hands off to the other. Sep 30, 2026 · 8 min read · Read → ## [Jev and the agentic web](https://ora.ai/blog/evaluating-jev) Agents with Jev making the step decisions and without it, across browser automation, WebMCP tools and NLWeb search: up to 4.3x faster and up to 13x cheaper, with the same task outcomes on WebMCP and NLWeb. Sep 24, 2026 · 11 min read · Read → ## [We partnered with Vercel to launch is-agentic.com](https://ora.ai/blog/is-agentic-with-vercel) We partnered with Vercel to launch is-agentic.com: a new agent readiness scanner tailored for the sites builders ship on Vercel, powered by the Ora ranking. Aug 20, 2026 · 3 min read · Read → ## [How Telnyx used Ora to grow agent signups](https://ora.ai/blog/telnyx-agent-readiness) Telnyx sits at #1 on the Ora leaderboard - 98 out of 100, grade A+ - and more than 30% of agent signups now convert to paid. This is how they got there. Jul 22, 2026 · 5 min read · Read → Case study ## [Deep Scan v2: we ran the agents, then scored what they did](https://ora.ai/blog/deep-scan-v2) The old scan sent agents to role-play our checklist on every run. It was our opinion, and it was slow. v2 flips it: we run real agents across thousands of intents and sites in our lab, learn where they succeed and stall, and reverse-engineer the score from that. The live scan now finishes in 20 to 30 seconds, and only signals we have verified agents rely on count. Jul 7, 2026 · 6 min read · Read → ## [What agents actually reach](https://ora.ai/blog/what-agents-actually-reach) Real agents lean hard on the human web - homepages and docs, in the same order a person would - and barely reach the files we built for them. Where those files do get reached, they convert better than anything. The bottleneck is discovery. Jun 16, 2026 · 5 min read · Read → ## [Deep Scan v1.1: every layer just got deeper](https://ora.ai/blog/deep-scan-v1-1) v1 ran real agents at every layer. v1.1 makes those agents work harder. Discovery is now a true AEO/GEO benchmark across answer engines. MCP gets graded on Anthropic's own best-practice guidelines, not just whether the endpoint responds. Some scores will drop. That's the point. May 13, 2026 · 4 min read · Read → ## [The state of agent readiness](https://ora.ai/blog/state-of-agent-readiness-2026) Agents are the new customers. We scored thousands of products on whether agents can actually work on their sites. 99% aren't ready. Here's what the 1% are doing differently. Apr 22, 2026 · 7 min read · Read → ## [Introducing Deep Scan: a benchmark, not a checklist](https://ora.ai/blog/introducing-deep-scan) Static scanners can tell you whether your site serves the right files. They can't tell you whether an agent picks you. Deep Scan spawns real agents at every layer of the AgentReady standard, from open-web discovery to multi-turn task completion, and grades on what they actually did. Apr 8, 2026 · 5 min read · Read → ## [Introducing AgentReady: the first open standard for agent readiness](https://ora.ai/blog/agentready-open-standard) The agentic web has a dozen protocols and no shared way to name what a product should implement. AgentReady is the first open standard for agent readiness: vendor-neutral, MIT-licensed, and deliberately separate from how anyone scores against it. Mar 20, 2026 · 4 min read · Read → Subscribe via RSS # Footer The standard for agent experience. © 2026 [era labs](https://eralabs.ai/) Product - Scan a site - [Journey](https://journey.ora.ai/) - [WebMCP audit](https://webmcp.ora.ai/) - [Directory](https://directory.ora.ai/) Resources - Methodology - Research - Blog - API Docs Company - About - Contact - Privacy - [@oradotai](https://x.com/oradotai)