Maze

Name: Maze AI agent readiness scorecard
Item: Maze
Rating: 84.3
Author: Stunt Double

Maze is a new type of security platform - built from scratch to use modern AI to make decisions, instead of pre-defined logic.

mazehq.com
AudienceB2B
MarketUS
Localeen-US

Agent score3.4

/100Good

Claim this domain

RankRank: Top 9%; #48
Developer tools rankDeveloper tools rank: Sector average 80.4; #5
Benchmark runsBenchmark runs: 6 providersAcross 6 providers; 1

Where this site sits

Developer tools avg: 80.4 (+3.9)
Market avg: 76.8 (+7.5)

Latest results

Maze ranks #48 of 553 scored sites.

Trend84.3 GoodOne run so far. The trend starts after the next one.Best agent82.7 GoodClaude on claude-opus-5-5. Llama trails at 38.1.Agent friction7improvementsMost serious: Agents searching for "Maze" do not find mazehq.com (Exa).Technical readiness83/1002 of 8 essential checks failing.Checks by Is Agentic

First run. The comparison starts after the next one.

This site
Developer tools
Market

By category

Brand awareness
90
Discovery
71
Information retrieval
91
Market ranking
63
Accuracy
96
Task completion
86
Contact & communication
80

Table view

Run	This site	Developer tools median	Market median
22 Oct 2026	84.3	79.1	79.9

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 36.0.

Site checks by category

Brand awareness: 71.0
Discovery: 87.0
Information retrieval: 86.0
Market ranking: 36.0
Accuracy: 100.0
Task completion: 63.0
Contact & communication: 60.0

01 Site checks

Points by category

Brand awareness71.0
Discovery87.0
Information retrieval86.0
Market ranking36.0
Accuracy100.0
Task completion63.0
Contact & communication60.0

Agent readiness checks

Essential: 65/80
Recommended: 14.4/20
Checks passing: 18/29

Markdown content negotiation (acceptmarkdown.com)Essential
Brand name discoverabilityRecommended
CLI tool availableRecommended
Rate limit response headersRecommended
Agent-friendly 404sEssential

02 Agent sessions

Brand awareness

Find the product name, what it helps developers do, and the languages, frameworks or platforms it supports.
Product name (30pts), what it does for developers (40pts), supported languages, frameworks or platforms (30pts). Deduct 20pts for hallucinations.
2m 21s
94median 94
Find the product name, what it helps developers do, and the languages, frameworks or platforms it supports.
Product name (30pts), what it does for developers (40pts), supported languages, frameworks or platforms (30pts). Deduct 20pts for hallucinations.
2m 49s
90median 94
Find the product name, what it helps developers do, and the languages, frameworks or platforms it supports.
Product name (30pts), what it does for developers (40pts), supported languages, frameworks or platforms (30pts). Deduct 20pts for hallucinations.
8m 25s
93median 94
Find the product name, what it helps developers do, and the languages, frameworks or platforms it supports.
Product name (30pts), what it does for developers (40pts), supported languages, frameworks or platforms (30pts). Deduct 20pts for hallucinations.
11m 34s
70median 94
Find the product name, what it helps developers do, and the languages, frameworks or platforms it supports.
Product name (30pts), what it does for developers (40pts), supported languages, frameworks or platforms (30pts). Deduct 20pts for hallucinations.
3m 53s
0median 94
Find the product name, what it helps developers do, and the languages, frameworks or platforms it supports.
Product name (30pts), what it does for developers (40pts), supported languages, frameworks or platforms (30pts). Deduct 20pts for hallucinations.
9m 48s
76median 94

Discovery

Navigate to the documentation and find the quickstart or getting-started guide, and note its URL and the first setup step it gives.
Found the docs within 2 nav hops (30pts). Reached the quickstart or getting-started guide within 4 hops (40pts). Correctly reported the first setup step (30pts). Deduct 20pts for each dead end.
35s
43median 76
Navigate to the documentation and find the quickstart or getting-started guide, and note its URL and the first setup step it gives.
Found the docs within 2 nav hops (30pts). Reached the quickstart or getting-started guide within 4 hops (40pts). Correctly reported the first setup step (30pts). Deduct 20pts for each dead end.
52s
43median 76
Navigate to the documentation and find the quickstart or getting-started guide, and note its URL and the first setup step it gives.
Found the docs within 2 nav hops (30pts). Reached the quickstart or getting-started guide within 4 hops (40pts). Correctly reported the first setup step (30pts). Deduct 20pts for each dead end.
2m 45s
58median 76
Navigate to the documentation and find the quickstart or getting-started guide, and note its URL and the first setup step it gives.
Found the docs within 2 nav hops (30pts). Reached the quickstart or getting-started guide within 4 hops (40pts). Correctly reported the first setup step (30pts). Deduct 20pts for each dead end.
6m 11s
0median 76
Navigate to the documentation and find the quickstart or getting-started guide, and note its URL and the first setup step it gives.
Found the docs within 2 nav hops (30pts). Reached the quickstart or getting-started guide within 4 hops (40pts). Correctly reported the first setup step (30pts). Deduct 20pts for each dead end.
1m 54s
26median 76
Navigate to the documentation and find the quickstart or getting-started guide, and note its URL and the first setup step it gives.
Found the docs within 2 nav hops (30pts). Reached the quickstart or getting-started guide within 4 hops (40pts). Correctly reported the first setup step (30pts). Deduct 20pts for each dead end.
4m 2s
0median 76

Information retrieval

Find the command or package name used to install it (npm, pip, brew, CLI download or similar), the latest released version or release…
Install command or package name (30pts), latest version or release date (30pts), free tier or licence (30pts). Correct and sourced from the site (10pts). Deduct 20pts for any hallucinated data.
2m 21s
90median 81
Find the command or package name used to install it (npm, pip, brew, CLI download or similar), the latest released version or release…
Install command or package name (30pts), latest version or release date (30pts), free tier or licence (30pts). Correct and sourced from the site (10pts). Deduct 20pts for any hallucinated data.
2m 48s
85median 81
Find the command or package name used to install it (npm, pip, brew, CLI download or similar), the latest released version or release…
Install command or package name (30pts), latest version or release date (30pts), free tier or licence (30pts). Correct and sourced from the site (10pts). Deduct 20pts for any hallucinated data.
8m 26s
93median 81

Market ranking

Based on your knowledge, name 3 direct competitors to mazehq.com in the same developer-tools category and rank them by developer adoption.
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 developer-tools category; cap the score at 40 if competitors are hallucinated or drawn from a different sector.
17s
58median 51
Based on your knowledge, name 3 direct competitors to mazehq.com in the same developer-tools category and rank them by developer adoption.
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 developer-tools category; cap the score at 40 if competitors are hallucinated or drawn from a different sector.
13s
76median 51
Based on your knowledge, name 3 direct competitors to mazehq.com in the same developer-tools category and rank them by developer adoption.
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 developer-tools category; cap the score at 40 if competitors are hallucinated or drawn from a different sector.
16s
51median 51

Accuracy

Find the rate limits or usage quotas that apply on the free or entry tier, and whether self-hosting is supported, reporting exactly what…
Answered the free or entry tier limits (50pts). Answered whether self-hosting is supported (50pts). Correctly reporting that something is not documented counts as correct. Deduct 40pts for invented limits or options.
2m 21s
96median 94
Find the rate limits or usage quotas that apply on the free or entry tier, and whether self-hosting is supported, reporting exactly what…
Answered the free or entry tier limits (50pts). Answered whether self-hosting is supported (50pts). Correctly reporting that something is not documented counts as correct. Deduct 40pts for invented limits or options.
2m 49s
90median 94
Find the rate limits or usage quotas that apply on the free or entry tier, and whether self-hosting is supported, reporting exactly what…
Answered the free or entry tier limits (50pts). Answered whether self-hosting is supported (50pts). Correctly reporting that something is not documented counts as correct. Deduct 40pts for invented limits or options.
8m 26s
93median 94

Task completion

Find the primary call-to-action for getting started (sign up, create an account, get an API key) and reach the signup form or first-run…
Found the primary CTA (20pts). Clicked through (20pts). Reached the signup form or first-run screen (40pts). Reported the URL and sign-in options or fields (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit.
36s
94median 88
Find the primary call-to-action for getting started (sign up, create an account, get an API key) and reach the signup form or first-run…
Found the primary CTA (20pts). Clicked through (20pts). Reached the signup form or first-run screen (40pts). Reported the URL and sign-in options or fields (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit.
52s
85median 88
Find the primary call-to-action for getting started (sign up, create an account, get an API key) and reach the signup form or first-run…
Found the primary CTA (20pts). Clicked through (20pts). Reached the signup form or first-run screen (40pts). Reported the URL and sign-in options or fields (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit.
2m 45s
85median 88
Find the primary call-to-action for getting started (sign up, create an account, get an API key) and reach the signup form or first-run…
Found the primary CTA (20pts). Clicked through (20pts). Reached the signup form or first-run screen (40pts). Reported the URL and sign-in options or fields (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit.
6m 11s
58median 88
Find the primary call-to-action for getting started (sign up, create an account, get an API key) and reach the signup form or first-run…
Found the primary CTA (20pts). Clicked through (20pts). Reached the signup form or first-run screen (40pts). Reported the URL and sign-in options or fields (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit.
1m 54s
58median 88
Find the primary call-to-action for getting started (sign up, create an account, get an API key) and reach the signup form or first-run…
Found the primary CTA (20pts). Clicked through (20pts). Reached the signup form or first-run screen (40pts). Reported the URL and sign-in options or fields (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit.
4m 3s
66median 88

03 Blend

Agents 60%
Checks 40%

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

Brand awareness11% of the overall
0.4 × 71.0 + 0.6 × 84.3 = 79.0 raw
79.0 raw → 89.9 published
Discovery17% of the overall
0.4 × 87.0 + 0.6 × 20.0 = 46.8 raw
46.8 raw → 71.1 published
Information retrieval17% of the overall
0.4 × 86.0 + 0.6 × 78.3 = 81.4 raw
81.4 raw → 91.2 published
Market ranking11% of the overall
0.4 × 36.0 + 0.6 × 35.7 = 35.8 raw
35.8 raw → 63.0 published
Accuracy17% of the overall
0.4 × 100.0 + 0.6 × 85.7 = 91.4 raw
91.4 raw → 96.0 published
Task completion22% of the overall
0.4 × 63.0 + 0.6 × 76.0 = 70.8 raw
70.8 raw → 85.6 published
Contact & communication6% of the overall
Site checks only: 60.0 raw
60.0 raw → 79.5 published

Category	Weight	Checks	Sessions	Blend	Benchmarked
Brand awareness	10%	71.0	84.3	79.0	89.9
Discovery	15%	87.0	20.0	46.8	71.1
Information retrieval	15%	86.0	78.3	81.4	91.2
Market ranking	10%	36.0	35.7	35.8	63.0
Accuracy	15%	100.0	85.7	91.4	96.0
Task completion	20%	63.0	76.0	70.8	85.6
Delegated access	10%	N/A
Contact & communication	5%	60.0	None	60.0	79.5
Overall	100%			~68.4	84.3

04 Benchmarked score

68.4 raw → 84.3

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

Category weights

Brand awareness 11%
Discovery 17%
Information retrieval 17%
Market ranking 11%
Accuracy 17%
Task completion 22%
Contact & communication 6%

Overall 84.3, from 68.4 raw points.

1 category does not apply to this site and is left out.

Agents

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

Claude
Latest run average
82.7
Developer tools median
100.0
Sessions
- Brand awareness
  Find the product name, what it helps developers do, and the languages, frameworks or platforms it supports.
  Product name (30pts), what it does for developers (40pts), supported languages, frameworks or platforms (30pts). Deduct 20pts for hallucinations.
  2m 21s
  94median 94
- Discovery
  Navigate to the documentation and find the quickstart or getting-started guide, and note its URL and the first setup step it gives.
  Found the docs within 2 nav hops (30pts). Reached the quickstart or getting-started guide within 4 hops (40pts). Correctly reported the first setup step (30pts). Deduct 20pts for each dead end.
  35s
  43median 76
- Information retrieval
  Find the command or package name used to install it (npm, pip, brew, CLI download or similar), the latest released version or release…
  Install command or package name (30pts), latest version or release date (30pts), free tier or licence (30pts). Correct and sourced from the site (10pts). Deduct 20pts for any hallucinated data.
  2m 21s
  90median 81
- Market ranking
  Based on your knowledge, name 3 direct competitors to mazehq.com in the same developer-tools category and rank them by developer adoption.
  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 developer-tools category; cap the score at 40 if competitors are hallucinated or drawn from a different sector.
  17s
  58median 51
- Accuracy
  Find the rate limits or usage quotas that apply on the free or entry tier, and whether self-hosting is supported, reporting exactly what…
  Answered the free or entry tier limits (50pts). Answered whether self-hosting is supported (50pts). Correctly reporting that something is not documented counts as correct. Deduct 40pts for invented limits or options.
  2m 21s
  96median 94
- Task completion
  Find the primary call-to-action for getting started (sign up, create an account, get an API key) and reach the signup form or first-run…
  Found the primary CTA (20pts). Clicked through (20pts). Reached the signup form or first-run screen (40pts). Reported the URL and sign-in options or fields (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit.
  36s
  94median 88
ChatGPT Agent
Latest run average
80.5
Developer tools median
100.0
Sessions
- Brand awareness
  Find the product name, what it helps developers do, and the languages, frameworks or platforms it supports.
  Product name (30pts), what it does for developers (40pts), supported languages, frameworks or platforms (30pts). Deduct 20pts for hallucinations.
  2m 49s
  90median 94
- Discovery
  Navigate to the documentation and find the quickstart or getting-started guide, and note its URL and the first setup step it gives.
  Found the docs within 2 nav hops (30pts). Reached the quickstart or getting-started guide within 4 hops (40pts). Correctly reported the first setup step (30pts). Deduct 20pts for each dead end.
  52s
  43median 76
- Information retrieval
  Find the command or package name used to install it (npm, pip, brew, CLI download or similar), the latest released version or release…
  Install command or package name (30pts), latest version or release date (30pts), free tier or licence (30pts). Correct and sourced from the site (10pts). Deduct 20pts for any hallucinated data.
  2m 48s
  85median 81
- Market ranking
  Based on your knowledge, name 3 direct competitors to mazehq.com in the same developer-tools category and rank them by developer adoption.
  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 developer-tools category; cap the score at 40 if competitors are hallucinated or drawn from a different sector.
  13s
  76median 51
- Accuracy
  Find the rate limits or usage quotas that apply on the free or entry tier, and whether self-hosting is supported, reporting exactly what…
  Answered the free or entry tier limits (50pts). Answered whether self-hosting is supported (50pts). Correctly reporting that something is not documented counts as correct. Deduct 40pts for invented limits or options.
  2m 49s
  90median 94
- Task completion
  Find the primary call-to-action for getting started (sign up, create an account, get an API key) and reach the signup form or first-run…
  Found the primary CTA (20pts). Clicked through (20pts). Reached the signup form or first-run screen (40pts). Reported the URL and sign-in options or fields (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit.
  52s
  85median 88
Gemini
Latest run average
81.1
Developer tools median
100.0
Sessions
- Brand awareness
  Find the product name, what it helps developers do, and the languages, frameworks or platforms it supports.
  Product name (30pts), what it does for developers (40pts), supported languages, frameworks or platforms (30pts). Deduct 20pts for hallucinations.
  8m 25s
  93median 94
- Discovery
  Navigate to the documentation and find the quickstart or getting-started guide, and note its URL and the first setup step it gives.
  Found the docs within 2 nav hops (30pts). Reached the quickstart or getting-started guide within 4 hops (40pts). Correctly reported the first setup step (30pts). Deduct 20pts for each dead end.
  2m 45s
  58median 76
- Information retrieval
  Find the command or package name used to install it (npm, pip, brew, CLI download or similar), the latest released version or release…
  Install command or package name (30pts), latest version or release date (30pts), free tier or licence (30pts). Correct and sourced from the site (10pts). Deduct 20pts for any hallucinated data.
  8m 26s
  93median 81
- Market ranking
  Based on your knowledge, name 3 direct competitors to mazehq.com in the same developer-tools category and rank them by developer adoption.
  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 developer-tools category; cap the score at 40 if competitors are hallucinated or drawn from a different sector.
  16s
  51median 51
- Accuracy
  Find the rate limits or usage quotas that apply on the free or entry tier, and whether self-hosting is supported, reporting exactly what…
  Answered the free or entry tier limits (50pts). Answered whether self-hosting is supported (50pts). Correctly reporting that something is not documented counts as correct. Deduct 40pts for invented limits or options.
  8m 26s
  93median 94
- Task completion
  Find the primary call-to-action for getting started (sign up, create an account, get an API key) and reach the signup form or first-run…
  Found the primary CTA (20pts). Clicked through (20pts). Reached the signup form or first-run screen (40pts). Reported the URL and sign-in options or fields (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit.
  2m 45s
  85median 88
Kimi
Latest run average
53.6
Developer tools median
86.4
Sessions
- Brand awareness
  Find the product name, what it helps developers do, and the languages, frameworks or platforms it supports.
  Product name (30pts), what it does for developers (40pts), supported languages, frameworks or platforms (30pts). Deduct 20pts for hallucinations.
  11m 34s
  70median 94
- Discovery
  Navigate to the documentation and find the quickstart or getting-started guide, and note its URL and the first setup step it gives.
  Found the docs within 2 nav hops (30pts). Reached the quickstart or getting-started guide within 4 hops (40pts). Correctly reported the first setup step (30pts). Deduct 20pts for each dead end.
  6m 11s
  0median 76
- Task completion
  Find the primary call-to-action for getting started (sign up, create an account, get an API key) and reach the signup form or first-run…
  Found the primary CTA (20pts). Clicked through (20pts). Reached the signup form or first-run screen (40pts). Reported the URL and sign-in options or fields (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit.
  6m 11s
  58median 88
Llama
Latest run average
38.1
Developer tools median
47.4
Sessions
- Brand awareness
  Find the product name, what it helps developers do, and the languages, frameworks or platforms it supports.
  Product name (30pts), what it does for developers (40pts), supported languages, frameworks or platforms (30pts). Deduct 20pts for hallucinations.
  3m 53s
  0median 94
- Discovery
  Navigate to the documentation and find the quickstart or getting-started guide, and note its URL and the first setup step it gives.
  Found the docs within 2 nav hops (30pts). Reached the quickstart or getting-started guide within 4 hops (40pts). Correctly reported the first setup step (30pts). Deduct 20pts for each dead end.
  1m 54s
  26median 76
- Task completion
  Find the primary call-to-action for getting started (sign up, create an account, get an API key) and reach the signup form or first-run…
  Found the primary CTA (20pts). Clicked through (20pts). Reached the signup form or first-run screen (40pts). Reported the URL and sign-in options or fields (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit.
  1m 54s
  58median 88
Grok
Latest run average
59.6
Developer tools median
85.7
Sessions
- Brand awareness
  Find the product name, what it helps developers do, and the languages, frameworks or platforms it supports.
  Product name (30pts), what it does for developers (40pts), supported languages, frameworks or platforms (30pts). Deduct 20pts for hallucinations.
  9m 48s
  76median 94
- Discovery
  Navigate to the documentation and find the quickstart or getting-started guide, and note its URL and the first setup step it gives.
  Found the docs within 2 nav hops (30pts). Reached the quickstart or getting-started guide within 4 hops (40pts). Correctly reported the first setup step (30pts). Deduct 20pts for each dead end.
  4m 2s
  0median 76
- Task completion
  Find the primary call-to-action for getting started (sign up, create an account, get an API key) and reach the signup form or first-run…
  Found the primary CTA (20pts). Clicked through (20pts). Reached the signup form or first-run screen (40pts). Reported the URL and sign-in options or fields (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit.
  4m 3s
  66median 88

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

Latest run 22 Oct 2026 (UTC). Sign in to request a re-run from 23 Oct 2026, 21:02 UTC.

Potential improvements

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

MediumBrand awareness

Agents searching for "Maze" do not find mazehq.com (Exa).

Biggest wins

Projected

Lifting Market ranking to Good adds about +0.8 on its own, taking the overall from 84.3 to 85.1.

Raise Market ranking from 63.0 to 72 (Good) to add about 0.8 to the overall score.
Raise Contact & communication from 79.5 to 85 (Excellent) to add about 0.3 to the overall score.
Raise Discovery from 71.1 to 72 (Good) to add about 0.1 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.

High: 0
Medium: 4
Low: 3

MediumBrand awareness
Agents searching for "Maze" do not find mazehq.com (Exa).
MediumMarket ranking
No Product/Service schema on the homepage. Agents can’t easily compare offerings.
MediumTask completion
No visible primary call-to-action in the server-rendered HTML. Agents have nothing concrete to click on behalf of a user.

4 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

2 of 8 essential checks fail. These are the files and signals agents read before they act.

Checks by Is Agentic

Score

83/ 100

Ready with a few material gaps

Essential: 6 of 8 pass
Recommended: 12 of 21 pass
Bonus: +3.5 from 16 positive signals

Investigate

Markdown content negotiation (acceptmarkdown.com)essential

Investigate

Brand name discoverabilityrecommended

Investigate

CLI tool availablerecommended

29 checks · scanned 2 Sept 2026

Technical readiness

Protocol baseline by Is Agentic

Score: 83/ 100; Ready with a few material gaps
Essential: 65/ 80; 6 of 8 passing
Recommended: 14.4/ 20; 12 of 21 passing
Bonus: +3.5; 16 positive signals

Investigate

Markdown content negotiation (acceptmarkdown.com)essential

Not acceptmarkdown.com compliant: Accept: text/markdown returned text/html; charset=utf-8; Vary header missing Accept (got "accept-encoding")

Fix: On the responses that serve text/markdown via Accept negotiation, add Accept to the Vary header (Vary: Accept, Accept-Encoding). Without it, CDNs can serve the cached HTML variant to an agent asking for markdown (or vice versa), depending on which variant landed in cache first.

Investigate

Brand name discoverabilityrecommended

"Maze" search returned 8 results but domain did not appear - brand may be too generic or not indexed

Fix: Make sure a clean search for your brand name returns your own domain in the top results. If it does not, your brand may be too generic, conflict with a more established term, or not yet indexed. Strengthen brand-name search by claiming consistent NAP across listings, earning press mentions that link to the canonical domain, and avoiding redirect chains that mask the apex domain in search results.

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

Rate limit response headersrecommended

No REST rate-limit headers found on probed endpoints (GraphQL signal: fail 0).

Fix: Return standard rate-limit headers on your API responses (the RFC RateLimit headers, plus Retry-After on a 429) so agents can self-throttle in real time, and document the conventions alongside your API.

Partial

Agent-friendly 404sessential

Nonexistent paths return a real HTTP 404. For full credit, include a short markdown body (site map links, where to look next) so agents can recover.

Fix: Return a real HTTP 404 (or 410) status for nonexistent paths - never a 200 with your app shell, which makes agents believe every path exists. For full credit, give the 404 response a short markdown body pointing agents at your sitemap, llms.txt, or docs index. Verify with `curl -s -o /dev/null -w "%{http_code}" https://yourdomain.com/some-path-that-does-not-exist` - it must print 404.

Partial

Developer resource discoverabilityrecommended

Name search surfaced no pages on mazehq.com, although developer resources exist on the site (API docs, OpenAPI spec, developer portal, MCP server) - weak search indexing or transient search noise

Fix: Make your developer resources (API docs, OpenAPI spec, auth docs, developer portal, MCP server) discoverable by name. Publish them at predictable URLs, list them in llms.txt, and include your product name in page titles and headings so search engines surface them for name-based queries.

Partial

REST typed error modelrecommended

Partial typed error model: error schema defined but not consistently referenced (or vice versa)

Fix: Document your error responses in your OpenAPI spec: give 4xx and 5xx responses a typed error schema (or use RFC 9457 application/problem+json). A consistent error object with a machine-readable code and a human-readable message lets agents handle failures without guessing.

Partial

Trust anchor pagesrecommended

About, Privacy pages verified - missing: Contact

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

API schema complexity analysisrecommended

REST: agent-friendly schema (22 operations, 100% with operationIds, 100% documented by description or summary) | GraphQL: introspection auth-gated and no schema evidence in docs | Combined score: 1/2

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.

Partial

REST versioning / deprecation policyrecommended

API versioning found (URL versioning (servers or paths)) but no deprecation or sunset policy detected - add Sunset/Deprecation headers or a deprecation policy page

Fix: Declare a versioning policy agents can rely on: version your API (in the URL path or a version header) and publish how you signal deprecation (a Sunset/Deprecation header or a documented timeline). Agents avoid integrating against a surface that can change without warning.

Partial

MCP server / manifestrecommended

Live MCP server at https://mcp.mazehq.com requires authentication (OAuth challenge at initialize) - properly scoped. Upgrade to public tool listing for full 6/6.

Fix: Build an MCP (Model Context Protocol) server exposing your API as tools. Use Streamable HTTP transport for full score. This lets Claude, ChatGPT, and other AI agents call your product natively.

29 checks · scanned 2 Sept 2026

Opportunity cost · developer tools

Maze could see ~$800,700 of new ARR exposed to agent-led journeys each year

Gap to leader: 15.7 pts
Above developer tools avg: 0.0 pts
Modeled new ARR at risk: $800,700

Claim Maze 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 mazehq.com

Paste this into Claude, ChatGPT, Cursor or Claude Code. It asks the question and tells your agent how to connect to the Index. No account needed.

Prompt

Look up mazehq.com on the Stunt Double Index. Tell me why it scores the way it does for AI agents, what its biggest frictions are, and what it should fix first. Use the Stunt Double Index MCP server for this: https://app.stuntdouble.io/api/mcp/index (Streamable HTTP, no sign-in). Its tools are get_index_report, list_index_sessions and search_index_domains. If it isn't connected yet: - If you can add MCP servers yourself (Claude Code, Cursor, VS Code), add it as "stunt-double-index", for example: claude mcp add --transport http stunt-double-index https://app.stuntdouble.io/api/mcp/index - Otherwise, tell me how to add it here, then wait. In Claude: Settings, Connectors, Add custom connector, paste the URL and leave the OAuth fields empty. In ChatGPT: turn on developer mode under Settings, Apps & Connectors, Advanced, then create a connector with the URL and No authentication. - If you can't use MCP at all, read https://index.stuntdouble.io/d/mazehq.com instead.

Setup for your client

Discover more insights with Stunt Double

Send AI agents through mazehq.com on your own tasks.

Try Stunt Double

Maze

By category

Points by category

Agent readiness checks

Brand awareness

Discovery

Information retrieval

Market ranking

Accuracy

Task completion

Category weights

Agents

Sessions

Sessions

Sessions

Sessions

Sessions

Sessions

Maze could see ~$800,700 of new ARR exposed to agent-led journeys each year

Show visitors your Good agent score

Ask your agent about mazehq.com