Carrd

Name: Carrd AI agent readiness scorecard
Item: Carrd
Rating: 77.5
Author: Stunt Double

A free platform for building simple, fully responsive one-page sites for pretty much anything.

carrd.co
AudienceDeveloper
Localeen

Agent score22.0

/100Good

Claim this domain

RankRank: Top 57%; #314
SaaS rankSaaS rank: Sector average 74.5; #129
Benchmark runsBenchmark runs: 3 providersAcross 3 providers; 5

Where this site sits

SaaS avg: 74.5 (+3.0)
Market avg: 76.7 (+0.8)

Latest results

Carrd ranks #314 of 550 scored sites, up 196 places since the last run.

Trend-7.8Since 14 May 2026, across 3 runs.Best agent100.0 ExcellentClaude. Gemini trails at 100.0.Agent friction13improvements1 high severity. Most serious: No discoverable MCP server. Agents and AI clients have no way to discover one automatically.Technical readiness46/1005 of 7 essential checks failing.Checks by Is Agentic

This site
SaaS
Market

Table view

Run	This site	SaaS median	Market median
12 Oct 2026	77.5	80.5	79.8
28 Sept 2026	55.5	76.5	76.4
14 May 2026	85.3	82.7	82.0

Monthly medians. Dates in UTC.

Performance

Site checks, then AI agents on real tasks.

Methodology

Automated checks probe the site before any agent runs. They count for 40% of each category. Strongest is Accuracy at 80.0, weakest is Delegated access at 37.0.

Site checks by category

Brand awareness: 55.0
Discovery: 64.0
Information retrieval: 74.0
Market ranking: 45.0
Accuracy: 80.0
Task completion: 77.0
Delegated access: 37.0
Contact & communication: 45.0

01 Site checks

Agent readiness checks

Essential: 36.2/80
Recommended: 8.9/20
Checks passing: 7/21

OpenAPI spec publishedEssential
JSON error responsesEssential
Markdown content negotiation (acceptmarkdown.com)Essential
JSON-LD structured dataRecommended
Agent instruction / when-to-useRecommended

02 Agent sessions

Brand awareness

Brand awareness
16s
98median 93
Brand awareness
29s
98median 93
Brand awareness
31s
98median 93

Discovery

Discovery
56s
90median 90
Discovery
1m 16s
82median 90
Discovery
1m 58s
70median 90

Information retrieval

Information retrieval
50s
94median 78
Information retrieval
48s
43median 78
Information retrieval
43s
62median 78

Market ranking

Market ranking
20s
73median 68
Market ranking
18s
56median 68
Market ranking
32s
76median 68

Accuracy

Accuracy
44s
88median 64
Accuracy
1m 12s
98median 64
Accuracy
2m 9s
21median 64

Task completion

Task completion
Running
Task completion
2m 33s
54median 87
Task completion
3m 42s
68median 87

Delegated access

Find the API reference and identify the supported OAuth scopes or API key permission levels.
Found the API reference (40pts). Correctly identified the auth model (40pts). Listed at least two specific scopes or permissions (20pts). Deduct 20pts if no API is available but that is the correct answer.
1m 28s
80median 90
Find the API reference and identify the supported OAuth scopes or API key permission levels.
Found the API reference (40pts). Correctly identified the auth model (40pts). Listed at least two specific scopes or permissions (20pts). Deduct 20pts if no API is available but that is the correct answer.
2m 36s
26median 90
Find the API reference and identify the supported OAuth scopes or API key permission levels.
Found the API reference (40pts). Correctly identified the auth model (40pts). Listed at least two specific scopes or permissions (20pts). Deduct 20pts if no API is available but that is the correct answer.
3m 18s
26median 90

Contact & communication

Find how to cancel the subscription and whether there is a pro-rated refund policy.
Found the cancellation path (50pts). Correctly described the refund or pro-ration policy (50pts). Deduct 20pts for each dead end or missing detail.
2m 23s
92median 80
Find how to cancel the subscription and whether there is a pro-rated refund policy.
Found the cancellation path (50pts). Correctly described the refund or pro-ration policy (50pts). Deduct 20pts for each dead end or missing detail.
2m 42s
93median 80
Find how to cancel the subscription and whether there is a pro-rated refund policy.
Found the cancellation path (50pts). Correctly described the refund or pro-ration policy (50pts). Deduct 20pts for each dead end or missing detail.
3m 44s
84median 80

03 Blend

Agents 60%
Checks 40%

One kind of evidence only? That kind counts in full.

Brand awareness10% of the overall
0.4 × 55.0 + 0.6 × 95.7 = 79.4 raw
79.4 raw → 90.1 published
Discovery15% of the overall
0.4 × 64.0 + 0.6 × 63.3 = 63.6 raw
63.6 raw → 81.6 published
Information retrieval15% of the overall
0.4 × 74.0 + 0.6 × 46.0 = 57.2 raw
57.2 raw → 77.8 published
Market ranking10% of the overall
0.4 × 45.0 + 0.6 × 44.3 = 44.6 raw
44.6 raw → 69.5 published
Accuracy15% of the overall
0.4 × 80.0 + 0.6 × 57.7 = 66.6 raw
66.6 raw → 83.3 published
Task completion20% of the overall
0.4 × 77.0 + 0.6 × 33.5 = 50.9 raw
50.9 raw → 73.8 published
Delegated access10% of the overall
0.4 × 37.0 + 0.6 × 23.3 = 28.8 raw
28.8 raw → 57.1 published
Contact & communication5% of the overall
0.4 × 45.0 + 0.6 × 78.3 = 65.0 raw
65.0 raw → 82.4 published

Category	Weight	Checks	Sessions	Blend	Benchmarked
Brand awareness	10%	55.0	95.7	79.4	90.1
Discovery	15%	64.0	63.3	63.6	81.6
Information retrieval	15%	74.0	46.0	57.2	77.8
Market ranking	10%	45.0	44.3	44.6	69.5
Accuracy	15%	80.0	57.7	66.6	83.3
Task completion	20%	77.0	33.5	50.9	73.8
Delegated access	10%	37.0	23.3	28.8	57.1
Contact & communication	5%	45.0	78.3	65.0	82.4
Overall	100%			~56.8	77.5

04 Benchmarked score

56.8 raw → 77.5

Final score is calibrated and adjusted to better reflect the actual performance and benchmark.

Overall 77.5, from 56.8 raw points.

Agents

Latest run in progress: 1 of 24 sessions to finish.

Claude
Latest run average
Run in progress
SaaS median
90.4
Sessions
- Brand awareness
  16s
  98median 93
- Discovery
  56s
  90median 90
- Information retrieval
  50s
  94median 78
- Market ranking
  20s
  73median 68
- Accuracy
  44s
  88median 64
- Task completion
- Delegated access
  Find the API reference and identify the supported OAuth scopes or API key permission levels.
  Found the API reference (40pts). Correctly identified the auth model (40pts). Listed at least two specific scopes or permissions (20pts). Deduct 20pts if no API is available but that is the correct answer.
  1m 28s
  80median 90
- Contact & communication
  Find how to cancel the subscription and whether there is a pro-rated refund policy.
  Found the cancellation path (50pts). Correctly described the refund or pro-ration policy (50pts). Deduct 20pts for each dead end or missing detail.
  2m 23s
  92median 80
ChatGPT Agent
Latest run average
74.4
SaaS median
90.4
Sessions
- Brand awareness
  29s
  98median 93
- Discovery
  1m 16s
  82median 90
- Information retrieval
  48s
  43median 78
- Market ranking
  18s
  56median 68
- Accuracy
  1m 12s
  98median 64
- Task completion
  2m 33s
  54median 87
- Delegated access
  Find the API reference and identify the supported OAuth scopes or API key permission levels.
  Found the API reference (40pts). Correctly identified the auth model (40pts). Listed at least two specific scopes or permissions (20pts). Deduct 20pts if no API is available but that is the correct answer.
  2m 36s
  26median 90
- Contact & communication
  Find how to cancel the subscription and whether there is a pro-rated refund policy.
  Found the cancellation path (50pts). Correctly described the refund or pro-ration policy (50pts). Deduct 20pts for each dead end or missing detail.
  2m 42s
  93median 80
Gemini
Latest run average
68.8
SaaS median
90.4
Sessions
- Brand awareness
  31s
  98median 93
- Discovery
  1m 58s
  70median 90
- Information retrieval
  43s
  62median 78
- Market ranking
  32s
  76median 68
- Accuracy
  2m 9s
  21median 64
- Task completion
  3m 42s
  68median 87
- Delegated access
  Find the API reference and identify the supported OAuth scopes or API key permission levels.
  Found the API reference (40pts). Correctly identified the auth model (40pts). Listed at least two specific scopes or permissions (20pts). Deduct 20pts if no API is available but that is the correct answer.
  3m 18s
  26median 90
- Contact & communication
  Find how to cancel the subscription and whether there is a pro-rated refund policy.
  Found the cancellation path (50pts). Correctly described the refund or pro-ration policy (50pts). Deduct 20pts for each dead end or missing detail.
  3m 44s
  84median 80

Excellent85+
Good72-84
OK58-71
Poor40-57
Critical<40

Potential improvements

Fix where agents got stuck, then lift your biggest categories.

HighDelegated access

No discoverable MCP server. Agents and AI clients have no way to discover one automatically.

Biggest wins

Projected

Lifting Task completion to Excellent adds about +2.3 on its own, taking the overall from 77.5 to 79.8.

Raise Task completion from 73.8 to 85 (Excellent) to add about 2.3 to the overall score.
Raise Information retrieval from 77.8 to 85 (Excellent) to add about 1.2 to the overall score.
Raise Discovery from 81.6 to 85 (Excellent) to add about 0.6 to the overall score.

Each gain assumes only that category improves. Fix several and the total lands a little under their sum.

Where agents get stuck

13 improvements from the latest run, 1 of them high severity.

High: 1
Medium: 7
Low: 5

HighDelegated access
No discoverable MCP server. Agents and AI clients have no way to discover one automatically.
MediumBrand awareness
No Organization JSON-LD. Agents can’t tell who owns the site at a glance.
MediumInformation retrieval
No JSON-LD structured data. Agents must infer entities from markup.

10 more, and the evidence for each

Want to find these in your own flows before an agent does? Read how to test your product for AI agent users.

Technical readiness

5 of 7 essential checks fail. These are the files and signals agents read before they act.

Checks by Is Agentic

Score

46/ 100

Agents are likely to struggle

Essential: 2 of 7 pass
Recommended: 5 of 14 pass
Bonus: +0.9 from 4 positive signals

Investigate

OpenAPI spec publishedessential

Investigate

JSON error responsesessential

Investigate

Markdown content negotiation (acceptmarkdown.com)essential

21 checks · scanned 9 Oct 2026

Technical readiness

Protocol baseline by Is Agentic

Score: 46/ 100; Agents are likely to struggle
Essential: 36.2/ 80; 2 of 7 passing
Recommended: 8.9/ 20; 5 of 14 passing
Bonus: +0.9; 4 positive signals

Investigate

OpenAPI spec publishedessential

No OpenAPI/Swagger specification found

Fix: Publish an OpenAPI (Swagger) specification at /openapi.json or /api/openapi.yaml. This is how agents understand your API surface automatically.

Investigate

JSON error responsesessential

API does not return JSON error responses (or no API detected)

Fix: Return structured JSON error responses with error codes, messages, and resolution hints. Agents can't parse HTML error pages.

Investigate

Markdown content negotiation (acceptmarkdown.com)essential

Homepage https://carrd.co does not meet the Markdown negotiation requirements: Accept: text/markdown returned text/html; charset=utf-8; Vary header missing Accept (got "accept-encoding")

Fix: Enable Markdown negotiation on the scanned homepage. Supporting it only on /docs or a separate .md URL does not satisfy this check. Requests with Accept: text/markdown must receive a nonempty Markdown body with Content-Type: text/markdown and Vary: Accept. Keep serving HTML for Accept: text/html. Adding Vary alone does not create a Markdown response. Verify both with `curl -sS -L -i -H 'Accept: text/markdown' https://yourdomain.com/` and `curl -sS -L -i -H 'Accept: text/html' https://yourdomain.com/`. Check the final response headers and body: Markdown with Vary: Accept for the first request, HTML for the second.

Investigate

JSON-LD structured datarecommended

No JSON-LD structured data found on homepage

Fix: Add JSON-LD structured data to your homepage using the identity type that matches your site - SoftwareApplication for products, Organization or LocalBusiness for companies, Person for personal sites, Article for blogs - with name, description, url, and type-appropriate fields (offers, sameAs, author) so AI can parse your identity programmatically.

Investigate

Agent instruction / when-to-userecommended

No agent instruction file with when-to-use guidance found

Fix: Tell agents when to reach for you: add a 'when to use this' section to your llms.txt (or a dedicated agent-instructions file) that names your best-fit use cases and how an agent should call you. Be specific about the jobs you are right for - generic marketing copy does not read as guidance.

Investigate

API schema complexity analysisrecommended

No API schema detected

Fix: Make your API spec self-describing: a unique operationId and a description on every operation, typed parameters, and response schemas. For GraphQL, a fully typed schema with a documented cost or rate limit reads best.

Investigate

Function calling compatibilityrecommended

No API spec found - function calling requires discoverable endpoints

Fix: Ensure API endpoints have unique operation IDs, typed schemas, and descriptions compatible with LLM function-calling formats.

Investigate

Sitemap existsrecommended

No sitemap found

Fix: Add a valid XML sitemap at /sitemap.xml listing all indexable URLs. Include lastmod dates and keep it under 50MB.

Investigate

Organization schema completenessrecommended

No JSON-LD found - Organization schema missing

Fix: Add Organization JSON-LD that includes both contactPoint (with email/phone and contactType) and address (PostalAddress). This lets AI verify your business legitimacy and answer contact queries.

Partial

Agent-friendly 404sessential

The nonexistent path https://carrd.co/__ora-404-probe-ogqyqonr correctly returns HTTP 404. Partial credit: no Markdown error body was detected.

Fix: Keep the correct HTTP 404 status. The remaining requirement is a Markdown error body when agents request Accept: text/markdown. Include at least 20 characters explaining the error and a link to your docs, sitemap, or llms.txt. Verify with `curl -sS -L -i -H 'Accept: text/markdown' https://yourdomain.com/some-path-that-does-not-exist`. Check both the final 404 status and the Markdown body with Content-Type: text/markdown. Checking the status alone does not verify the missing requirement.

Partial

Content without JavaScriptessential

1506 chars with H1, but first content heading is H2, not H1

Fix: Serve at least 500 characters of meaningful homepage content in raw HTML. Add a clear H1, keep deeper heading levels sequential, and remove excessive non-content markup.

Partial

Developer resource discoverabilityrecommended

Agent found 9 pages by name but no recognizable developer-resource type. Found on site but absent from this search sample: developer portal. Not found in this search sample: API docs, OpenAPI spec, auth docs, MCP server, SDK documentation

Fix: Check whether your developer resources (API docs, OpenAPI spec, auth docs, developer portal, MCP server, SDK documentation) surface in name-based searches. If they do not, use predictable URLs, link them in llms.txt, and include your product name in page titles and headings. This result reflects one search sample.

Partial

Public API with reachable endpointsrecommended

API described in documentation at https://docs.carrd.co but no machine-verifiable API surface confirmed. Best-of-protocols score: 3/7.

Fix: Expose a public REST or GraphQL API. AI agents need programmatic access - not just a web UI - to integrate with your product.

Partial

Metadata completenessrecommended

3/4 metadata signals present - missing: og:type

Fix: Add all four signals to your homepage: <link rel="canonical">, <html lang="...">, <meta property="og:image">, and <meta property="og:type">. Agents use these for entity resolution and attribution.

21 checks · scanned 9 Oct 2026

Opportunity cost · SaaS

Carrd could see ~$1,530,000 of new ARR exposed to agent-led journeys each year

Gap to leader: 22.5 pts
Above SaaS avg: 0.0 pts
Modeled new ARR at risk: $1,530,000

Claim Carrd to use your own new ARR

Badge

Show visitors your Good agent score

Add a live Index badge to your footer, docs or README. The badge updates after every run and links visitors to this scorecard.

Ask your agent about carrd.co

Add the Index to Claude, ChatGPT or Cursor as an MCP connector to look up any score, frictions and agent sessions. No account needed.

https://app.stuntdouble.io/api/mcp/index

Setup for your client

Discover more insights with Stunt Double

Send AI agents through carrd.co on your own tasks.

Try Stunt Double

Carrd

Latest results

By category

Performance

Points by category

Agent readiness checks

Brand awareness

Discovery

Information retrieval

Market ranking

Accuracy

Task completion

Delegated access

Contact & communication

Category weights

Agents

Sessions

Sessions

Sessions

Potential improvements

Biggest wins

Where agents get stuck

Technical readiness

Carrd could see ~$1,530,000 of new ARR exposed to agent-led journeys each year

Show visitors your Good agent score

Ask your agent about carrd.co