Stunt Double Index

Name: Stunt Double Index AI agent readiness scorecard
Item: Stunt Double Index
Rating: 78.3
Author: Stunt Double

The independent ranking of how real AI agents experience the world's websites across discovery, information retrieval, task completion, delegated access and more.

index.stuntdouble.io
AudienceDeveloper
MarketsUS, AU
Localesen-US, en-AU

Agent score1.0

/100Good

RankRank: Top 54%; #295
SaaS rankSaaS rank: Sector average 74.5; #126
Benchmark runsBenchmark runs: 3 providersAcross 3 providers; 8

Where this site sits

SaaS avg: 74.5 (+3.8)
Market avg: 76.7 (+1.6)

Latest results

Stunt Double Index ranks #295 of 550 scored sites, up 2 places since the last run.

Trend+2.8Since 29 Sept 2026, across 3 runs.Best agent98.6 ExcellentClaude on claude-sonnet-5. Gemini trails at 98.6.Agent friction4improvementsMost serious: Pricing only available if JavaScript is enabled. Agents may report "pricing not disclosed".Technical readiness64/1007 of 13 essential checks failing.Checks by Is Agentic

This site
SaaS
Market

Table view

Run	This site	SaaS median	Market median
12 Oct 2026	78.3	80.5	79.8
30 Sept 2026	77.3	76.5	76.4
29 Sept 2026	75.5	76.5	76.4

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 100.0, weakest is Market ranking at 40.0.

Site checks by category

Brand awareness: 95.0
Discovery: 77.0
Information retrieval: 84.0
Market ranking: 40.0
Accuracy: 100.0
Task completion: 81.0
Delegated access: 82.0
Contact & communication: 90.0

01 Site checks

Agent readiness checks

Essential: 44.1/80
Recommended: 14.5/20
Checks passing: 18/32

OpenAPI spec publishedEssential
JSON error responsesEssential
MCP App view reachableEssential
MCP App view CSPEssential
Markdown content negotiation (acceptmarkdown.com)Essential

02 Agent sessions

Brand awareness

Find the brand name, a one-sentence description of what they sell, and the primary product category.
Did the agent identify the brand (40pts), describe the product offering accurately (40pts), and name the product category (20pts)? Deduct 20pts for any hallucinated claim.
2m 42s
98median 93
Find the brand name, a one-sentence description of what they sell, and the primary product category.
Did the agent identify the brand (40pts), describe the product offering accurately (40pts), and name the product category (20pts)? Deduct 20pts for any hallucinated claim.
10m 56s
100median 93
Find the brand name, a one-sentence description of what they sell, and the primary product category.
Did the agent identify the brand (40pts), describe the product offering accurately (40pts), and name the product category (20pts)? Deduct 20pts for any hallucinated claim.
7m 12s
88median 93
Find the brand name, a one-sentence description of what they sell, and the primary product category.
Did the agent identify the brand (40pts), describe the product offering accurately (40pts), and name the product category (20pts)? Deduct 20pts for any hallucinated claim.
16m 28s
88median 93

Discovery

Navigate to the top-selling products or best sellers page, and note its URL and page heading.
Found the correct page within 3 nav hops (60pts). Correctly identified it as the best sellers / top products page (40pts). Deduct 20pts for each dead end.
1m 57s
0median 90
Navigate to the top-selling products or best sellers page, and note its URL and page heading.
Found the correct page within 3 nav hops (60pts). Correctly identified it as the best sellers / top products page (40pts). Deduct 20pts for each dead end.
4m 30s
26median 90
Navigate to the top-selling products or best sellers page, and note its URL and page heading.
Found the correct page within 3 nav hops (60pts). Correctly identified it as the best sellers / top products page (40pts). Deduct 20pts for each dead end.
5m 24s
58median 90
Navigate to the top-selling products or best sellers page, and note its URL and page heading.
Found the correct page within 3 nav hops (60pts). Correctly identified it as the best sellers / top products page (40pts). Deduct 20pts for each dead end.
11m
58median 90

Information retrieval

Find the return policy timeframe in days, the available shipping options, and the price of at least one product.
Return policy timeframe (30pts), shipping options (30pts), a product price (30pts). Correct and sourced from the site (10pts). Deduct 20pts for any hallucinated data.
2m 37s
36median 78
Find the return policy timeframe in days, the available shipping options, and the price of at least one product.
Return policy timeframe (30pts), shipping options (30pts), a product price (30pts). Correct and sourced from the site (10pts). Deduct 20pts for any hallucinated data.
10m 55s
62median 78
Find the return policy timeframe in days, the available shipping options, and the price of at least one product.
Return policy timeframe (30pts), shipping options (30pts), a product price (30pts). Correct and sourced from the site (10pts). Deduct 20pts for any hallucinated data.
7m 13s
76median 78

Market ranking

Based on your knowledge, name 3 direct competitors to index.stuntdouble.io in the ecommerce space and rank them by market share.
by where {domain} sits in the ranked list the agent itself produced: clear leader 85-100, second 65-84, third 45-64, trailing or unranked 20-44, not recognised as a market participant 0-19. Require at least 3 plausible direct competitors from the same ecommerce space; cap the score at 40 if competitors are hallucinated or drawn from a different sector.
11s
43median 68
Based on your knowledge, name 3 direct competitors to index.stuntdouble.io in the ecommerce space and rank them by market share.
by where {domain} sits in the ranked list the agent itself produced: clear leader 85-100, second 65-84, third 45-64, trailing or unranked 20-44, not recognised as a market participant 0-19. Require at least 3 plausible direct competitors from the same ecommerce space; cap the score at 40 if competitors are hallucinated or drawn from a different sector.
18s
43median 68
Based on your knowledge, name 3 direct competitors to index.stuntdouble.io in the ecommerce space and rank them by market share.
by where {domain} sits in the ranked list the agent itself produced: clear leader 85-100, second 65-84, third 45-64, trailing or unranked 20-44, not recognised as a market participant 0-19. Require at least 3 plausible direct competitors from the same ecommerce space; cap the score at 40 if competitors are hallucinated or drawn from a different sector.
12s
36median 68

Accuracy

Find the free-shipping threshold, and any countries or regions explicitly excluded from free shipping.
Answered the free-shipping threshold and exclusions question (50pts). Answer was factually correct and sourced from the site (50pts). Deduct 40pts for hallucinations or invented thresholds.
2m 37s
100median 64
Find the free-shipping threshold, and any countries or regions explicitly excluded from free shipping.
Answered the free-shipping threshold and exclusions question (50pts). Answer was factually correct and sourced from the site (50pts). Deduct 40pts for hallucinations or invented thresholds.
10m 56s
100median 64
Find the free-shipping threshold, and any countries or regions explicitly excluded from free shipping.
Answered the free-shipping threshold and exclusions question (50pts). Answer was factually correct and sourced from the site (50pts). Deduct 40pts for hallucinations or invented thresholds.
7m 11s
85median 64

Task completion

Pick any product (from that page if you can), add it to the cart, and proceed to checkout as a guest up to but not including the payment…
Found a product (20pts). Added to cart (20pts). Reached the checkout or payment form (40pts). Reported the URL and form description (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit that blocked progress.
1m 57s
0median 87
Pick any product (from that page if you can), add it to the cart, and proceed to checkout as a guest up to but not including the payment…
Found a product (20pts). Added to cart (20pts). Reached the checkout or payment form (40pts). Reported the URL and form description (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit that blocked progress.
4m 32s
49median 87
Pick any product (from that page if you can), add it to the cart, and proceed to checkout as a guest up to but not including the payment…
Found a product (20pts). Added to cart (20pts). Reached the checkout or payment form (40pts). Reported the URL and form description (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit that blocked progress.
5m 24s
49median 87
Pick any product (from that page if you can), add it to the cart, and proceed to checkout as a guest up to but not including the payment…
Found a product (20pts). Added to cart (20pts). Reached the checkout or payment form (40pts). Reported the URL and form description (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit that blocked progress.
10m 59s
43median 87

Delegated access

Find the developer or API documentation.
Found the API documentation (40pts). Correctly identified the auth model (API key, OAuth, none) (40pts). Named any specific scopes or endpoints available (20pts). Deduct 20pts if no API is available but that is the correct answer.
1m 34s
96median 90
Find the developer or API documentation.
Found the API documentation (40pts). Correctly identified the auth model (API key, OAuth, none) (40pts). Named any specific scopes or endpoints available (20pts). Deduct 20pts if no API is available but that is the correct answer.
2m 39s
94median 90
Find the developer or API documentation.
Found the API documentation (40pts). Correctly identified the auth model (API key, OAuth, none) (40pts). Named any specific scopes or endpoints available (20pts). Deduct 20pts if no API is available but that is the correct answer.
3m 23s
93median 90
Find the developer or API documentation.
Found the API documentation (40pts). Correctly identified the auth model (API key, OAuth, none) (40pts). Named any specific scopes or endpoints available (20pts). Deduct 20pts if no API is available but that is the correct answer.
7m 40s
54median 90

Contact & communication

Find how to request a return and what the eligibility conditions are (timeframe, item condition, exceptions).
Found the path to initiate a return (50pts). Extracted the eligibility conditions including timeframe and any exceptions (50pts). Deduct 20pts for each dead end or missing condition.
1m 59s
26median 80
Find how to request a return and what the eligibility conditions are (timeframe, item condition, exceptions).
Found the path to initiate a return (50pts). Extracted the eligibility conditions including timeframe and any exceptions (50pts). Deduct 20pts for each dead end or missing condition.
1m 21s
36median 80
Find how to request a return and what the eligibility conditions are (timeframe, item condition, exceptions).
Found the path to initiate a return (50pts). Extracted the eligibility conditions including timeframe and any exceptions (50pts). Deduct 20pts for each dead end or missing condition.
3m 59s
43median 80

03 Blend

Agents 60%
Checks 40%

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

Brand awareness10% of the overall
0.4 × 95.0 + 0.6 × 90.0 = 92.0 raw
92.0 raw → 96.3 published
Discovery15% of the overall
0.4 × 77.0 + 0.6 × 11.7 = 37.8 raw
37.8 raw → 64.5 published
Information retrieval15% of the overall
0.4 × 84.0 + 0.6 × 33.3 = 53.6 raw
53.6 raw → 75.5 published
Market ranking10% of the overall
0.4 × 40.0 + 0.6 × 13.3 = 24.0 raw
24.0 raw → 52.6 published
Accuracy15% of the overall
0.4 × 100.0 + 0.6 × 90.0 = 94.0 raw
94.0 raw → 97.3 published
Task completion20% of the overall
0.4 × 81.0 + 0.6 × 13.3 = 40.4 raw
40.4 raw → 66.5 published
Delegated access10% of the overall
0.4 × 82.0 + 0.6 × 88.3 = 85.8 raw
85.8 raw → 93.3 published
Contact & communication5% of the overall
0.4 × 90.0 + 0.6 × 7.5 = 40.5 raw
40.5 raw → 66.6 published

Category	Weight	Checks	Sessions	Blend	Benchmarked
Brand awareness	10%	95.0	90.0	92.0	96.3
Discovery	15%	77.0	11.7	37.8	64.5
Information retrieval	15%	84.0	33.3	53.6	75.5
Market ranking	10%	40.0	13.3	24.0	52.6
Accuracy	15%	100.0	90.0	94.0	97.3
Task completion	20%	81.0	13.3	40.4	66.5
Delegated access	10%	82.0	88.3	85.8	93.3
Contact & communication	5%	90.0	7.5	40.5	66.6
Overall	100%			~58.1	78.3

04 Benchmarked score

58.1 raw → 78.3

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

Overall 78.3, from 58.1 raw points.

Agents

Each agent’s score over 30 days, and how its latest sessions went.

Claude
Latest run average
69.5
SaaS median
90.4
Sessions
- Brand awareness
  Find the brand name, a one-sentence description of what they sell, and the primary product category.
  Did the agent identify the brand (40pts), describe the product offering accurately (40pts), and name the product category (20pts)? Deduct 20pts for any hallucinated claim.
  2m 42s
  Replay session
  98median 93
- Discovery
  Navigate to the top-selling products or best sellers page, and note its URL and page heading.
  Found the correct page within 3 nav hops (60pts). Correctly identified it as the best sellers / top products page (40pts). Deduct 20pts for each dead end.
  1m 57s
  Replay session
  0median 90
- Information retrieval
  Find the return policy timeframe in days, the available shipping options, and the price of at least one product.
  Return policy timeframe (30pts), shipping options (30pts), a product price (30pts). Correct and sourced from the site (10pts). Deduct 20pts for any hallucinated data.
  2m 37s
  Replay session
  36median 78
- Market ranking
  Based on your knowledge, name 3 direct competitors to index.stuntdouble.io in the ecommerce space and rank them by market share.
  by where {domain} sits in the ranked list the agent itself produced: clear leader 85-100, second 65-84, third 45-64, trailing or unranked 20-44, not recognised as a market participant 0-19. Require at least 3 plausible direct competitors from the same ecommerce space; cap the score at 40 if competitors are hallucinated or drawn from a different sector.
  11s
  Replay session
  43median 68
- Accuracy
  Find the free-shipping threshold, and any countries or regions explicitly excluded from free shipping.
  Answered the free-shipping threshold and exclusions question (50pts). Answer was factually correct and sourced from the site (50pts). Deduct 40pts for hallucinations or invented thresholds.
  2m 37s
  Replay session
  100median 64
- Task completion
  Pick any product (from that page if you can), add it to the cart, and proceed to checkout as a guest up to but not including the payment…
  Found a product (20pts). Added to cart (20pts). Reached the checkout or payment form (40pts). Reported the URL and form description (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit that blocked progress.
  1m 57s
  Replay session
  0median 87
- Delegated access
  Find the developer or API documentation.
  Found the API documentation (40pts). Correctly identified the auth model (API key, OAuth, none) (40pts). Named any specific scopes or endpoints available (20pts). Deduct 20pts if no API is available but that is the correct answer.
  1m 34s
  Replay session
  96median 90
ChatGPT Agent
Latest run average
70.5
SaaS median
90.4
Sessions
- Brand awareness
  Find the brand name, a one-sentence description of what they sell, and the primary product category.
  Did the agent identify the brand (40pts), describe the product offering accurately (40pts), and name the product category (20pts)? Deduct 20pts for any hallucinated claim.
  10m 56s
  Replay session
  100median 93
- Discovery
  Navigate to the top-selling products or best sellers page, and note its URL and page heading.
  Found the correct page within 3 nav hops (60pts). Correctly identified it as the best sellers / top products page (40pts). Deduct 20pts for each dead end.
  4m 30s
  Replay session
  26median 90
- Information retrieval
  Find the return policy timeframe in days, the available shipping options, and the price of at least one product.
  Return policy timeframe (30pts), shipping options (30pts), a product price (30pts). Correct and sourced from the site (10pts). Deduct 20pts for any hallucinated data.
  10m 55s
  Replay session
  62median 78
- Market ranking
  Based on your knowledge, name 3 direct competitors to index.stuntdouble.io in the ecommerce space and rank them by market share.
  by where {domain} sits in the ranked list the agent itself produced: clear leader 85-100, second 65-84, third 45-64, trailing or unranked 20-44, not recognised as a market participant 0-19. Require at least 3 plausible direct competitors from the same ecommerce space; cap the score at 40 if competitors are hallucinated or drawn from a different sector.
  18s
  Replay session
  43median 68
- Accuracy
  Find the free-shipping threshold, and any countries or regions explicitly excluded from free shipping.
  Answered the free-shipping threshold and exclusions question (50pts). Answer was factually correct and sourced from the site (50pts). Deduct 40pts for hallucinations or invented thresholds.
  10m 56s
  Replay session
  100median 64
- Task completion
  Pick any product (from that page if you can), add it to the cart, and proceed to checkout as a guest up to but not including the payment…
  Found a product (20pts). Added to cart (20pts). Reached the checkout or payment form (40pts). Reported the URL and form description (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit that blocked progress.
  4m 32s
  Replay session
  49median 87
- Delegated access
  Find the developer or API documentation.
  Found the API documentation (40pts). Correctly identified the auth model (API key, OAuth, none) (40pts). Named any specific scopes or endpoints available (20pts). Deduct 20pts if no API is available but that is the correct answer.
  2m 39s
  Replay session
  94median 90
- Contact & communication
  Find how to request a return and what the eligibility conditions are (timeframe, item condition, exceptions).
  Found the path to initiate a return (50pts). Extracted the eligibility conditions including timeframe and any exceptions (50pts). Deduct 20pts for each dead end or missing condition.
  1m 59s
  Replay session
  26median 80
Gemini
Latest run average
69.4
SaaS median
90.4
Sessions
- Brand awareness
  Find the brand name, a one-sentence description of what they sell, and the primary product category.
  Did the agent identify the brand (40pts), describe the product offering accurately (40pts), and name the product category (20pts)? Deduct 20pts for any hallucinated claim.
  7m 12s
  Replay session
  88median 93
- Discovery
  Navigate to the top-selling products or best sellers page, and note its URL and page heading.
  Found the correct page within 3 nav hops (60pts). Correctly identified it as the best sellers / top products page (40pts). Deduct 20pts for each dead end.
  5m 24s
  Replay session
  58median 90
- Information retrieval
  Find the return policy timeframe in days, the available shipping options, and the price of at least one product.
  Return policy timeframe (30pts), shipping options (30pts), a product price (30pts). Correct and sourced from the site (10pts). Deduct 20pts for any hallucinated data.
  7m 13s
  Replay session
  76median 78
- Market ranking
  Based on your knowledge, name 3 direct competitors to index.stuntdouble.io in the ecommerce space and rank them by market share.
  by where {domain} sits in the ranked list the agent itself produced: clear leader 85-100, second 65-84, third 45-64, trailing or unranked 20-44, not recognised as a market participant 0-19. Require at least 3 plausible direct competitors from the same ecommerce space; cap the score at 40 if competitors are hallucinated or drawn from a different sector.
  12s
  Replay session
  36median 68
- Accuracy
  Find the free-shipping threshold, and any countries or regions explicitly excluded from free shipping.
  Answered the free-shipping threshold and exclusions question (50pts). Answer was factually correct and sourced from the site (50pts). Deduct 40pts for hallucinations or invented thresholds.
  7m 11s
  Replay session
  85median 64
- Task completion
  Pick any product (from that page if you can), add it to the cart, and proceed to checkout as a guest up to but not including the payment…
  Found a product (20pts). Added to cart (20pts). Reached the checkout or payment form (40pts). Reported the URL and form description (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit that blocked progress.
  5m 24s
  Replay session
  49median 87
- Delegated access
  Find the developer or API documentation.
  Found the API documentation (40pts). Correctly identified the auth model (API key, OAuth, none) (40pts). Named any specific scopes or endpoints available (20pts). Deduct 20pts if no API is available but that is the correct answer.
  3m 23s
  Replay session
  93median 90
- Contact & communication
  Find how to request a return and what the eligibility conditions are (timeframe, item condition, exceptions).
  Found the path to initiate a return (50pts). Extracted the eligibility conditions including timeframe and any exceptions (50pts). Deduct 20pts for each dead end or missing condition.
  1m 21s
  Replay session
  36median 80
Kimi
Latest run average
59.9
SaaS median
83.8
Sessions
- Brand awareness
  Find the brand name, a one-sentence description of what they sell, and the primary product category.
  Did the agent identify the brand (40pts), describe the product offering accurately (40pts), and name the product category (20pts)? Deduct 20pts for any hallucinated claim.
  16m 28s
  Replay session
  88median 93
- Discovery
  Navigate to the top-selling products or best sellers page, and note its URL and page heading.
  Found the correct page within 3 nav hops (60pts). Correctly identified it as the best sellers / top products page (40pts). Deduct 20pts for each dead end.
  11m
  Replay session
  58median 90
- Task completion
  Pick any product (from that page if you can), add it to the cart, and proceed to checkout as a guest up to but not including the payment…
  Found a product (20pts). Added to cart (20pts). Reached the checkout or payment form (40pts). Reported the URL and form description (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit that blocked progress.
  10m 59s
  Replay session
  43median 87
- Delegated access
  Find the developer or API documentation.
  Found the API documentation (40pts). Correctly identified the auth model (API key, OAuth, none) (40pts). Named any specific scopes or endpoints available (20pts). Deduct 20pts if no API is available but that is the correct answer.
  7m 40s
  Replay session
  54median 90
- Contact & communication
  Find how to request a return and what the eligibility conditions are (timeframe, item condition, exceptions).
  Found the path to initiate a return (50pts). Extracted the eligibility conditions including timeframe and any exceptions (50pts). Deduct 20pts for each dead end or missing condition.
  3m 59s
  Replay session
  43median 80

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

Latest run 12 Oct 2026 (UTC). Sign in to request a re-run, once a day.

Potential improvements

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

MediumMarket ranking

Pricing only available if JavaScript is enabled. Agents may report "pricing not disclosed".

Biggest wins

Projected

Lifting Information retrieval to Excellent adds about +1.5 on its own, taking the overall from 78.3 to 79.8.

Raise Information retrieval from 75.5 to 85 (Excellent) to add about 1.5 to the overall score.
Raise Discovery from 64.5 to 72 (Good) to add about 1.0 to the overall score.
Raise Task completion from 66.5 to 72 (Good) to add about 0.9 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

4 improvements from the latest run.

High: 0
Medium: 2
Low: 2

MediumMarket ranking
Pricing only available if JavaScript is enabled. Agents may report "pricing not disclosed".
MediumTask completion
No visible primary call-to-action in the server-rendered HTML. Agents have nothing concrete to click on behalf of a user.
LowDiscovery
Agents searching for what index.stuntdouble.io does do not find it (Exa).

1 more, and the evidence for each

What the agent saw

Screens from the lowest-scoring session in the latest run.

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

Technical readiness

7 of 13 essential checks fail. These are the files and signals agents read before they act.

Checks by Is Agentic

Score

64/ 100

Important blockers remain

Essential: 6 of 13 pass
Recommended: 12 of 19 pass
Bonus: +5 from 35 positive signals

Investigate

OpenAPI spec publishedessential

Investigate

JSON error responsesessential

Investigate

MCP App view reachableessential

32 checks · scanned 9 Oct 2026

Technical readiness

Protocol baseline by Is Agentic

Score: 64/ 100; Important blockers remain
Essential: 44.1/ 80; 6 of 13 passing
Recommended: 14.5/ 20; 12 of 19 passing
Bonus: +5; 35 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

MCP App view reachableessential

MCP App declared but no view source found (no ui:// resource with HTML content)

Fix: Make sure your MCP App view is reachable and public. For inline ui:// resources: return HTML with <!DOCTYPE html> and no login form. For external HTTP origins (referenced via <base href> or <meta refresh>): return 200 OK + text/html without requiring auth (no 401/403, no password input in the body).

Investigate

MCP App view CSPessential

No ui:// view could be read - cannot evaluate the CSP it declares

Fix: Declare your view's CSP in _meta.ui.csp on the ui:// resource's resources/read content item, using the camelCase origin lists: connectDomains (fetch and WebSocket targets), resourceDomains (scripts, styles, images, fonts, media), frameDomains (nested iframes), and baseUriDomains. List specific origins such as https://api.example.com or https://*.example.com, never * or a bare scheme like https:. If the view makes no network calls and loads no external assets, leave csp out and hosts apply their restrictive default. Hosts build the iframe's CSP from this declaration, so a CSP in the view's own HTML does not replace it, and browsers ignore frame-ancestors in a <meta> tag.

Investigate

Markdown content negotiation (acceptmarkdown.com)essential

Homepage https://index.stuntdouble.io does not meet the Markdown negotiation requirements: Accept: text/markdown returned text/html; charset=utf-8; Vary header missing Accept (got "rsc, next-router-state-tree, next-router-prefetch, next-router-segment-prefetch")

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

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

CLI tool availablerecommended

No CLI tool found

Fix: Publish an official CLI tool on npm, PyPI, or Homebrew. A CLI lets agents and developers script interactions with your product without building API integrations from scratch.

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.

Partial

Agent-friendly 404sessential

The nonexistent path https://index.stuntdouble.io/__ora-404-probe-08n92960 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

3734 chars with H1, but 2.1% content ratio is below the 5% target

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

Organization schema completenessrecommended

Organization schema found but missing: address

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 onboarding frictionrecommended

Onboarding signals described but not verified live: self-serve key generation, sandbox/test environment

Fix: Offer a free tier or trial, self-serve API key generation, and a sandbox environment. Agents can't fill out 'contact sales' forms.

Partial

JSON-LD structured datarecommended

JSON-LD Organization found - missing description on this entity

Fix: Add description to the Organization JSON-LD entity for full score.

32 checks · scanned 9 Oct 2026

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 index.stuntdouble.io

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 index.stuntdouble.io on your own tasks.

Try Stunt Double

Stunt Double Index

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

Sessions

Potential improvements

Biggest wins

Where agents get stuck

What the agent saw

Technical readiness

Show visitors your Good agent score

Ask your agent about index.stuntdouble.io