actual.ai

Visit

Agent readiness reportDeveloper Tools

86/100A · Strong

  • Discovery17/20
  • Access29/30
  • Usability31/40
  • PaymentsBonus
Rank
#38of 360
In Developer Tools
#2of 29
Last 7 days
+1212 points · +78 places
Scanned
Nov 172026
What the scan found
Agent access is the strongest area, with an OpenAPI spec and developer portal, while brand name discoverability and an MCP server or manifest are the biggest gaps.

Where the score comes from

77 of 90 points

How actual.ai scores on each of the four questions agents ask.

Discovery17/20

Access29/30

Usability31/40

Paymentsnot scored yet

Strongest

Access

Content without JavaScript, A2A / agent-card, and 3 more are missing.

29/30

Most to gain

Usability

auth.md walkthrough simulation, Agent auth discovery metadata, and 9 more are missing.

31/40

Most to gain

Discovery

ARD trust manifest, Brand name discoverability, and 1 more are missing.

17/20

Not scored yet

Payments ( bonus )

6 checks partly met. Counts when scoring opens.

—

Agent path

How an agent movedthrough the site

We asked an agent a question about actual.aiand recorded every request it made.

Aactual.aiAnsweredRan Nov 4, 2026

Question

I want to start using Actual AI (actual.ai). Find its setup and getting-started guide.

4
Steps
29s
Duration
4
Pages opened
0
Failed

Every link it followed loaded.

Where the address came fromPage it asked forWhat came backNamed in the question1 stepA link on a page it read3 stepsTyped by the agent0 stepsactual.ai /actual.ai //developers/developers/cli/docs/cli/docs/auth.md/auth.mdRead4 stepsDidn’t load0 steps
  1. 1actual.ai /Named in the question → Read
  2. 2/developersA link on a page it read → Read
  3. 3/cli/docsA link on a page it read → Read
  4. 4/auth.mdA link on a page it read → Read
4/4 steps
StepsHow it found itCame back as
Step 4 of 4
actual.ai/auth.md
How it got here
A link on a page it read
Response
200
Came back as
Markdown

How it found each page

Named in the question1

A link on a page it read3

Typed by the agent0

A search result0

What it reached

Home pageStep 1

PricingNever reached

DocsNever reached

Its answer

Answers aren’t shown publicly

See what agents answer about your own site.

Run agents on your site and read every answer, with every page they opened.

Get started →

Free to start. No card.

Discovery17 of 202 to fix1 partly5 passed
ARD trust manifestRecommended0 / 2
Wikipedia / Wikidata entity presenceRecommended0 / 4
Brand name discoverabilityRequired1 / 3
ARD discoveryRequired1 / 1
ARD entry validityRecommended2 / 2
Developer resource discoverabilityRecommended3 / 3
robots.txt AI crawler policyRequired2 / 2
NPM/PyPI SDK packageRecommended1 / 1
+ 7 checks not in the score
AI Catalog discoveryRecommendedNot counted
Category share of voiceRecommendedNot counted
Listed in MCP registriesRecommendedNot counted
Agent platform configsEmergingNot counted
Agent Plugins manifestEmergingNot counted
Registry brandingEmergingNot counted
ChatGPT app listedRecommendedNot counted
Access29 of 302 to fix3 partly22 passed
A2A / agent-cardRecommended0 / 2
MCP well-known discoveryRecommended0 / 2
Content without JavaScriptRequired2 / 3
Sitemap freshness (lastmod)Recommended0 / 1
llms.txt links resolveRecommended1 / 2
Sitemap existsRequired2 / 2
Not blocked by bot detectionRequired2 / 2
Agent discovery fileRequired2 / 2
HTTP Link headers (RFC 8288)Required1 / 1
robots.txt agent-user policyRequired2 / 2
llms.txt existsRequired1 / 1
llms.txt formattingRecommended2 / 2
JSON-LD structured dataRequired4 / 4
Pricing info accessibleRequired3 / 3
Public API/docs linked from homepageRequired3 / 3
JSON-LD entity linking (sameAs)Recommended2 / 2
Metadata completenessRequired2 / 2
Organization schema completenessRecommended2 / 2
Schema type breadthRecommended2 / 2
Trust anchor pagesRequired2 / 2
Redirect hygieneRecommended1 / 1
Page token budgetRecommended1 / 1
OpenAPI spec publishedRequired7 / 7
Developer portalRecommended6 / 6
API catalog (RFC 9727)Required2 / 2
Markdown content negotiation (acceptmarkdown.com)Recommended1 / 1
Agent crawler reachabilityRecommended2 / 2
+ 15 checks not in the score
Agent Skills index conformance (v0.2.0)EmergingNot counted
Listed on skills.shEmergingNot counted
pricing.md existsEmergingNot counted
NLWeb Schema FeedsEmergingNot counted
Agent mode viewEmergingNot counted
Markdown URL fallbackEmergingNot counted
Modular llms.txt per product areaEmergingNot counted
Agent instruction / when-to-useRequiredNot counted
Skills.sh skill qualityEmergingNot counted
Markdown alternate linkEmergingNot counted
Markdown frontmatter metadataEmergingNot counted
Code fence validityEmergingNot counted
Content behind authRecommendedNot counted
Markdown agent docsEmergingNot counted
Bot-UA markdown servingEmergingNot counted
Usability31 of 406 to fix5 partly16 passed
agent_auth endpoints reachableRecommended0 / 2
MCP server / manifestRequired0 / 6
Idempotency-Key supportRecommended0 / 3
REST async-job patternRecommended0 / 2
Sandbox / test environmentRecommended0 / 2
REST batch / bulk endpointRecommended0 / 2
auth.md walkthrough simulationRecommended1 / 2
Agent auth discovery metadataRecommended1 / 3
REST versioning / deprecation policyRecommended1 / 3
CLI tool availableRecommended2 / 3
Agent-friendly 404sRecommended1 / 2
Public API with reachable endpointsRequired7 / 7
OAuth 2.0 supportRequired5 / 5
Scoped permissionsRecommended5 / 5
Agent onboarding frictionRecommended2 / 2
OAuth Protected Resource metadata (RFC 9728)Required2 / 2
auth.md existsRequired2 / 2
auth.md structureRecommended2 / 2
Agent auth WWW-Authenticate hintRecommended1 / 1
WebMCP supportRequired5 / 5
Rate limit response headersRecommended2 / 2
JSON error responsesRequired4 / 4
REST typed error modelRecommended3 / 3
Accessible document structureRecommended3 / 3
Accessible names on controlsRecommended2 / 2
API schema complexity analysisRecommended2 / 2
Function calling compatibilityRecommended2 / 2
+ 35 checks not in the score
MCP tool descriptionsRecommendedNot counted
MCP parameter schemasRecommendedNot counted
MCP server identityRecommendedNot counted
MCP tool listingRecommendedNot counted
MCP tool namingRecommendedNot counted
MCP auth mechanismRecommendedNot counted
MCP OAuth metadataRecommendedNot counted
MCP PKCE S256 supportRecommendedNot counted
Web Bot Auth directoryEmergingNot counted
MCP error handlingRecommendedNot counted
MCP modern transportRecommendedNot counted
REST pagination patternRecommendedNot counted
Multi-language SDK packagesRecommendedNot counted
NLWeb /ask endpointEmergingNot counted
NLWeb streaming supportEmergingNot counted
REST response schema coverageRecommendedNot counted
MCP tool annotationsRecommendedNot counted
MCP server-card.jsonRecommendedNot counted
Product + docs MCP coverageRecommendedNot counted
MCP resources exposedRecommendedNot counted
GraphQL typed error modelRecommendedNot counted
GraphQL versioning / deprecation policyRecommendedNot counted
GraphQL pagination patternRecommendedNot counted
GraphQL async-job patternRecommendedNot counted
GraphQL schema description coverageRecommendedNot counted
GraphQL batch mutationsRecommendedNot counted
Native interactive controlsRecommendedNot counted
Form control labelingRecommendedNot counted
Accessibility-tree injection safety (bonus)RecommendedNot counted
MCP Apps supportRecommendedNot counted
A2UI / generative UI supportEmergingNot counted
MCP Apps UI qualityRecommendedNot counted
MCP App view reachableRecommendedNot counted
MCP App view CSPRecommendedNot counted
MCP resource qualityRecommendedNot counted
PaymentsNot scored yet6 partly
MPP payment protocolRequired0 / 2
x402 payment protocolRequired0 / 2
UCP - Universal Commerce ProtocolRequired0 / 3
ACP - Agentic Commerce ProtocolRequired0 / 3
ACP delegate paymentRecommended0 / 3
AP2 - Agent Payments ProtocolRecommended0 / 3

Field notes on agent users, every other week.

The newest agent journey teardowns, straight to your inbox. No launches, no fluff.

One email every two weeks. Unsubscribe anytime.