Ora blog
Partnership announcement6 min
Ora Partners with MIT's NandaIndex to Build the Open Agentic Web
The agentic web needs more than a way to find things. It needs a way to find the right things, understand what they can do, and actually use them. Today, Ora is joining NandaIndex as a launch partner to help build that future.
Read →Earlier posts
Announcement5 min
Introducing AgentReady.org: the first open standard for AX
AgentReady is an open standard for what a product should implement so agents can use it, built from measured agent behavior. We maintain it with Vercel, Stripe, Auth0, Mintlify, Tavily, Google, Elementor, and MIT.
Research paper12 min
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.
Experiment8 min
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.
Research11 min
Jev and the agentic web
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.
Announcement3 min
We partnered with Vercel to launch is-agentic.com
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.
Case study5 min
How Telnyx used Ora to grow agent signups
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.
Research brief6 min
Deep Scan v2: we ran the agents, then scored what they did
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.
Research brief5 min
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.
Research brief4 min
Deep Scan v1.1: every layer just got deeper
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.
Research brief7 min
The state of agent readiness
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.
Research brief5 min
Introducing Deep Scan: a benchmark, not a checklist
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.