ora
LeaderboardJourneyNewDirectoryNewResearch

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.

We don't guess these checks. We measure them.

In our research lab we spawn real agents across thousands of intents and sites, then watch where they succeed and where they stall. Every check below is reverse-engineered from what actually moved an agent's success.

Measured behavior, not opinion.

progress

0 / 100 pts

Discovery - 20 pts1Accessibility - 30 pts2Usability - 40 pts3Payments - 10 pts4
1

Discovery

20 pts

Can an agent find and recommend you?

When an agent needs a product or service to finish a task, it searches and picks from the options it can find and trust.

If agents can't find you when they search for what you do - or have never heard of you - they pick someone else.

2

Accessibility

30 pts

Can it access your data and understand you?

After landing, the agent builds a mental model: what your product is, who it is for, what it costs, and what its API looks like - all from the surfaces it can actually fetch and read.

Blocked crawlers, JS-only content, and weak structure create hallucinated positioning, wrong recommendations, and low citation confidence.

3

Usability

40 pts

Can it use you - operate, authenticate, integrate?

Intent becomes execution when the agent can authenticate, operate your product, and hand back a usable experience when a human steps in - over an API, an MCP server, or the GUI itself.

Broken auth, missing endpoints, or weak handoff UX create dead ends at the exact moment user value should happen.

4

Payments

10 pts

Can it pay you?

For products agents can buy or meter, the last step is the transaction itself: the agent pays for the thing it just did on the user's behalf.

If there is no machine-payable path, an agent that got all the way to checkout hands the task back to a human - or completes it with a competitor that can take the payment.

6

Grade & Badge

0-100

What does the final number mean?

The four layers collapse into a single score and letter grade. It tells you exactly where an agent's journey breaks and how far it gets before giving up.

A low grade means agents route elsewhere.

ora scores each layer based on how many checks passed, then combines them into a single number from 0 to 100.

A+

95-100

Leading

A

86-94

Agent-Ready

B

70-85

Competitive

C

48-69

Needs Work

D

28-47

At Risk

F

0-27

Unusable

what happens next

Agents use the score

After the scan, agents query ora in real time to decide who to work with. They compare candidates, check feedback from other agents, and route to the product that scored highest.

Scan your site →
Read the docs
© 2026 era labs. All rights reserved.
AboutBlogDocsMethodologyPrivacyContact