Four/Four

Name: Four/Four AI agent readiness scorecard
Item: Four/Four
Rating: 87.7
Author: Stunt Double

Aggregate unstructured feedback from real customer conversations at massive scale. Expose key pain points, new opportunities and make decisions fast to drive growth

fourfour.ai
AudienceDeveloper
Localeen

Agent score0.2

/100Excellent

RankRank: Top 8%; #46
SaaS rankSaaS rank: Sector average 74.5; #36
Benchmark runsBenchmark runs: 5 providersAcross 5 providers; 4

Where this site sits

SaaS avg: 74.5 (+13.2)
Market avg: 76.7 (+11.0)

Latest results

Four/Four ranks #46 of 550 scored sites, down 21 places since the last run.

Trend-0.1Since 3 Oct 2026, across 3 runs.Best agent87.9 ExcellentGemini on gemini-3.8-flash. Llama trails at 54.7.Agent friction7improvements1 high severity. Most serious: No discoverable MCP server. Agents and AI clients have no way to discover one automatically.Technical readiness58/1006 of 10 essential checks failing.Checks by Is Agentic

This site
SaaS
Market

Table view

Run	This site	SaaS median	Market median
5 Oct 2026	87.7	80.5	79.8
4 Oct 2026	87.9	80.5	79.8
3 Oct 2026	87.8	80.5	79.8

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 50.0.

Site checks by category

Brand awareness: 82.0
Discovery: 58.0
Information retrieval: 78.0
Market ranking: 50.0
Accuracy: 100.0
Task completion: 78.0
Delegated access: 59.0
Contact & communication: 85.0

01 Site checks

Agent readiness checks

Essential: 38.7/80
Recommended: 15.1/20
Checks passing: 16/29

OpenAPI spec publishedEssential
Scoped permissionsEssential
JSON error responsesEssential
Markdown content negotiation (acceptmarkdown.com)Essential
CLI tool availableRecommended

02 Agent sessions

Brand awareness

Find the product name, its one-sentence value proposition, and the primary user persona it targets.
Did the agent correctly identify the product name (30pts), the value prop (40pts), and the target user (30pts)? Deduct 20pts for hallucinations.
1m 26s
94median 93
Find the product name, its one-sentence value proposition, and the primary user persona it targets.
Did the agent correctly identify the product name (30pts), the value prop (40pts), and the target user (30pts)? Deduct 20pts for hallucinations.
2m 55s
94median 93
Find the product name, its one-sentence value proposition, and the primary user persona it targets.
Did the agent correctly identify the product name (30pts), the value prop (40pts), and the target user (30pts)? Deduct 20pts for hallucinations.
10m 35s
36median 93
Find the product name, its one-sentence value proposition, and the primary user persona it targets.
Did the agent correctly identify the product name (30pts), the value prop (40pts), and the target user (30pts)? Deduct 20pts for hallucinations.
5m 20s
0median 93

Discovery

Navigate to the pricing page, and note its URL and the names of any pricing tiers shown.
Found the pricing page within 3 nav hops (60pts). Correctly identified it as the pricing page and listed at least one tier (40pts). Deduct 20pts for each dead end.
43s
98median 89
Navigate to the pricing page, and note its URL and the names of any pricing tiers shown.
Found the pricing page within 3 nav hops (60pts). Correctly identified it as the pricing page and listed at least one tier (40pts). Deduct 20pts for each dead end.
39s
98median 89
Navigate to the pricing page, and note its URL and the names of any pricing tiers shown.
Found the pricing page within 3 nav hops (60pts). Correctly identified it as the pricing page and listed at least one tier (40pts). Deduct 20pts for each dead end.
2m 33s
95median 89
Navigate to the pricing page, and note its URL and the names of any pricing tiers shown.
Found the pricing page within 3 nav hops (60pts). Correctly identified it as the pricing page and listed at least one tier (40pts). Deduct 20pts for each dead end.
3m 15s
94median 89

Information retrieval

Find the starter or free tier price, one headline feature of the product, and the length of any free trial offered.
Starter/free price (30pts), headline feature (30pts), trial length (30pts). Correct and sourced from the site (10pts). Deduct 20pts for any hallucinated data.
1m 29s
82median 78
Find the starter or free tier price, one headline feature of the product, and the length of any free trial offered.
Starter/free price (30pts), headline feature (30pts), trial length (30pts). Correct and sourced from the site (10pts). Deduct 20pts for any hallucinated data.
2m 56s
94median 78

Market ranking

Based on your knowledge, name 3 direct competitors to fourfour.ai in the SaaS 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 SaaS space; cap the score at 40 if competitors are hallucinated or drawn from a different sector.
10s
32median 68
Based on your knowledge, name 3 direct competitors to fourfour.ai in the SaaS 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 SaaS space; cap the score at 40 if competitors are hallucinated or drawn from a different sector.
8s
32median 68

Accuracy

Find out whether individual users can access the Enterprise tier, and the specific SSO options listed for Enterprise.
Answered whether individuals can access Enterprise (50pts). Listed the specific SSO options correctly (50pts). Deduct 40pts for hallucinations or invented features.
1m 29s
80median 64
Find out whether individual users can access the Enterprise tier, and the specific SSO options listed for Enterprise.
Answered whether individuals can access Enterprise (50pts). Listed the specific SSO options correctly (50pts). Deduct 40pts for hallucinations or invented features.
2m 56s
80median 64

Task completion

Click the primary CTA for any paid plan and reach the signup or upgrade form.
Found the pricing page (20pts). Clicked the primary CTA (20pts). Reached the signup/upgrade form (40pts). Reported the URL and form fields (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit.
43s
98median 86
Click the primary CTA for any paid plan and reach the signup or upgrade form.
Found the pricing page (20pts). Clicked the primary CTA (20pts). Reached the signup/upgrade form (40pts). Reported the URL and form fields (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit.
39s
96median 86
Click the primary CTA for any paid plan and reach the signup or upgrade form.
Found the pricing page (20pts). Clicked the primary CTA (20pts). Reached the signup/upgrade form (40pts). Reported the URL and form fields (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit.
2m 33s
96median 86
Click the primary CTA for any paid plan and reach the signup or upgrade form.
Found the pricing page (20pts). Clicked the primary CTA (20pts). Reached the signup/upgrade form (40pts). Reported the URL and form fields (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit.
3m 14s
66median 86

03 Blend

Agents 60%
Checks 40%

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

Brand awareness10% of the overall
0.4 × 82.0 + 0.6 × 87.0 = 85.0 raw
85.0 raw → 92.9 published
Discovery15% of the overall
0.4 × 58.0 + 0.6 × 95.7 = 80.6 raw
80.6 raw → 90.8 published
Information retrieval15% of the overall
0.4 × 78.0 + 0.6 × 72.7 = 74.8 raw
74.8 raw → 87.8 published
Market ranking10% of the overall
0.4 × 50.0 + 0.6 × 8.0 = 24.8 raw
24.8 raw → 53.4 published
Accuracy15% of the overall
0.4 × 100.0 + 0.6 × 60.0 = 76.0 raw
76.0 raw → 88.4 published
Task completion20% of the overall
0.4 × 78.0 + 0.6 × 93.3 = 87.2 raw
87.2 raw → 94.0 published
Delegated access10% of the overall
0.4 × 59.0 + 0.6 × 88.0 = 76.4 raw
76.4 raw → 88.6 published
Contact & communication5% of the overall
0.4 × 85.0 + 0.6 × 72.0 = 77.2 raw
77.2 raw → 89.0 published

Category	Weight	Checks	Sessions	Blend	Benchmarked
Brand awareness	10%	82.0	87.0	85.0	92.9
Discovery	15%	58.0	95.7	80.6	90.8
Information retrieval	15%	78.0	72.7	74.8	87.8
Market ranking	10%	50.0	8.0	24.8	53.4
Accuracy	15%	100.0	60.0	76.0	88.4
Task completion	20%	78.0	93.3	87.2	94.0
Delegated access	10%	59.0	88.0	76.4	88.6
Contact & communication	5%	85.0	72.0	77.2	89.0
Overall	100%			~74.6	87.7

04 Benchmarked score

74.6 raw → 87.7

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

Overall 87.7, from 74.6 raw points.

Agents

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

Claude
Latest run average
No sessions in the latest run
SaaS median
90.4
Sessions
No Claude sessions in the latest run, so its score comes from earlier runs.
ChatGPT Agent
Latest run average
84.5
SaaS median
90.4
Sessions
- Brand awareness
  Find the product name, its one-sentence value proposition, and the primary user persona it targets.
  Did the agent correctly identify the product name (30pts), the value prop (40pts), and the target user (30pts)? Deduct 20pts for hallucinations.
  1m 26s
  Replay session
  94median 93
- Discovery
  Navigate to the pricing page, and note its URL and the names of any pricing tiers shown.
  Found the pricing page within 3 nav hops (60pts). Correctly identified it as the pricing page and listed at least one tier (40pts). Deduct 20pts for each dead end.
  43s
  Replay session
  98median 89
- Information retrieval
  Find the starter or free tier price, one headline feature of the product, and the length of any free trial offered.
  Starter/free price (30pts), headline feature (30pts), trial length (30pts). Correct and sourced from the site (10pts). Deduct 20pts for any hallucinated data.
  1m 29s
  Replay session
  82median 78
- Market ranking
  Based on your knowledge, name 3 direct competitors to fourfour.ai in the SaaS 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 SaaS space; cap the score at 40 if competitors are hallucinated or drawn from a different sector.
  10s
  Replay session
  32median 68
- Accuracy
  Find out whether individual users can access the Enterprise tier, and the specific SSO options listed for Enterprise.
  Answered whether individuals can access Enterprise (50pts). Listed the specific SSO options correctly (50pts). Deduct 40pts for hallucinations or invented features.
  1m 29s
  Replay session
  80median 64
- Task completion
  Click the primary CTA for any paid plan and reach the signup or upgrade form.
  Found the pricing page (20pts). Clicked the primary CTA (20pts). Reached the signup/upgrade form (40pts). Reported the URL and form fields (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit.
  43s
  Replay session
  98median 86
Gemini
Latest run average
86.3
SaaS median
90.4
Sessions
- Brand awareness
  Find the product name, its one-sentence value proposition, and the primary user persona it targets.
  Did the agent correctly identify the product name (30pts), the value prop (40pts), and the target user (30pts)? Deduct 20pts for hallucinations.
  2m 55s
  Replay session
  94median 93
- Discovery
  Navigate to the pricing page, and note its URL and the names of any pricing tiers shown.
  Found the pricing page within 3 nav hops (60pts). Correctly identified it as the pricing page and listed at least one tier (40pts). Deduct 20pts for each dead end.
  39s
  Replay session
  98median 89
- Information retrieval
  Find the starter or free tier price, one headline feature of the product, and the length of any free trial offered.
  Starter/free price (30pts), headline feature (30pts), trial length (30pts). Correct and sourced from the site (10pts). Deduct 20pts for any hallucinated data.
  2m 56s
  Replay session
  94median 78
- Market ranking
  Based on your knowledge, name 3 direct competitors to fourfour.ai in the SaaS 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 SaaS space; cap the score at 40 if competitors are hallucinated or drawn from a different sector.
  8s
  Replay session
  32median 68
- Accuracy
  Find out whether individual users can access the Enterprise tier, and the specific SSO options listed for Enterprise.
  Answered whether individuals can access Enterprise (50pts). Listed the specific SSO options correctly (50pts). Deduct 40pts for hallucinations or invented features.
  2m 56s
  Replay session
  80median 64
- Task completion
  Click the primary CTA for any paid plan and reach the signup or upgrade form.
  Found the pricing page (20pts). Clicked the primary CTA (20pts). Reached the signup/upgrade form (40pts). Reported the URL and form fields (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit.
  39s
  Replay session
  96median 86
Kimi
Latest run average
81.8
SaaS median
84.0
Sessions
- Brand awareness
  Find the product name, its one-sentence value proposition, and the primary user persona it targets.
  Did the agent correctly identify the product name (30pts), the value prop (40pts), and the target user (30pts)? Deduct 20pts for hallucinations.
  10m 35s
  Replay session
  36median 93
- Discovery
  Navigate to the pricing page, and note its URL and the names of any pricing tiers shown.
  Found the pricing page within 3 nav hops (60pts). Correctly identified it as the pricing page and listed at least one tier (40pts). Deduct 20pts for each dead end.
  2m 33s
  Replay session
  95median 89
- Task completion
  Click the primary CTA for any paid plan and reach the signup or upgrade form.
  Found the pricing page (20pts). Clicked the primary CTA (20pts). Reached the signup/upgrade form (40pts). Reported the URL and form fields (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit.
  2m 33s
  Replay session
  96median 86
Llama
Latest run average
68.2
SaaS median
58.5
Sessions
- Brand awareness
  Find the product name, its one-sentence value proposition, and the primary user persona it targets.
  Did the agent correctly identify the product name (30pts), the value prop (40pts), and the target user (30pts)? Deduct 20pts for hallucinations.
  5m 20s
  Replay session
  0median 93
- Discovery
  Navigate to the pricing page, and note its URL and the names of any pricing tiers shown.
  Found the pricing page within 3 nav hops (60pts). Correctly identified it as the pricing page and listed at least one tier (40pts). Deduct 20pts for each dead end.
  3m 15s
  Replay session
  94median 89
- Task completion
  Click the primary CTA for any paid plan and reach the signup or upgrade form.
  Found the pricing page (20pts). Clicked the primary CTA (20pts). Reached the signup/upgrade form (40pts). Reported the URL and form fields (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit.
  3m 14s
  Replay session
  66median 86

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

Latest run 5 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.

HighDelegated access

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

Biggest wins

Projected

Lifting Market ranking to OK adds about +0.2 on its own, taking the overall from 87.7 to 87.9.

Raise Market ranking from 53.4 to 58 (OK) to add about 0.2 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

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

High: 1
Medium: 2
Low: 4

HighDelegated access
No discoverable MCP server. Agents and AI clients have no way to discover one automatically.
MediumDiscovery
No robots.txt. Agents fall back to defaults and may miss crawl hints.
MediumMarket ranking
Pricing only available if JavaScript is enabled. Agents may report "pricing not disclosed".

4 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

6 of 10 essential checks fail. These are the files and signals agents read before they act.

Checks by Is Agentic

Score

58/ 100

Important blockers remain

Essential: 4 of 10 pass
Recommended: 12 of 19 pass
Bonus: +3.7 from 16 positive signals

Investigate

OpenAPI spec publishedessential

Investigate

Scoped permissionsessential

Investigate

JSON error responsesessential

29 checks · scanned 13 Oct 2026

Technical readiness

Protocol baseline by Is Agentic

Score: 58/ 100; Important blockers remain
Essential: 38.7/ 80; 4 of 10 passing
Recommended: 15.1/ 20; 12 of 19 passing
Bonus: +3.7; 16 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

Scoped permissionsessential

No declared OAuth scopes, security schemes, or scoped-permission documentation found

Fix: Declare scoped API permissions where machines can read them: named OAuth scopes in your OpenAPI security schemes, or scopes_supported in RFC 9728 protected-resource metadata. Prose descriptions of roles help humans, but agents need the machine-readable declaration to request least-privilege access.

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://fourfour.ai 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

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

Content without JavaScriptessential

4389 chars of readable text, but no H1 tag

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

Agent-friendly 404sessential

The nonexistent path https://fourfour.ai/__ora-404-probe-mqtpiv9v 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

Agent onboarding frictionrecommended

Onboarding signals described but not verified live: free tier available, self-serve key generation

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

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

Trust anchor pagesrecommended

Contact, Privacy pages verified - missing: About

Fix: Publish real /about, /contact, and /privacy pages with at least 500 characters of content each. These are the pages AI agents check to verify your business is legitimate before recommending you.

Partial

MCP server / manifestrecommended

MCP server detected at https://fourfour.ai/mcp; it requires authentication. Presence is verified (5/6), but Ora could not inspect its tools or verify access scopes without credentials.

Fix: Keep authentication enabled. Verify tool listing with an authorized MCP client. This unauthenticated scan cannot establish whether protected tools are missing or unusable.

29 checks · scanned 13 Oct 2026

Badge

Show visitors your Excellent 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 fourfour.ai

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 fourfour.ai on your own tasks.

Try Stunt Double

Four/Four

Latest results

By category

Performance

Points by category

Agent readiness checks

Brand awareness

Discovery

Information retrieval

Market ranking

Accuracy

Task completion

Category weights

Agents

Sessions

Sessions

Sessions

Sessions

Sessions

Potential improvements

Biggest wins

Where agents get stuck

What the agent saw

Technical readiness

Show visitors your Excellent agent score

Ask your agent about fourfour.ai