Ca

Name: Ca AI agent readiness scorecard
Item: Ca
Rating: 70.2
Author: Stunt Double

dmv.ca.gov

Agent score7.7

/100OK

Claim this domain

RankRank: Top 79%; #437
Government rankGovernment rank: Sector average 77.8; #14
Benchmark runsBenchmark runs: 3 providersAcross 3 providers; 5

Where this site sits

Government avg: 77.8 (−7.6)
Market avg: 76.7 (−6.5)

Latest results

Ca ranks #437 of 550 scored sites, up 29 places since the last run.

Trend-0.1Since 14 May 2026, across 3 runs.Best agent90.4 ExcellentClaude. Gemini trails at 90.4.Agent friction19improvements2 high severity. Most serious: Homepage ships little text to server-rendered HTML. Agents without a browser see an empty shell.Technical readiness35/1004 of 6 essential checks failing.Checks by Is Agentic

This site
Government
Market

Table view

Run	This site	Government median	Market median
12 Oct 2026	70.2	78.3	79.8
28 Sept 2026	62.5	71.3	76.4
14 May 2026	70.3	n/a	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. With no sessions yet, they count in full. Strongest is Discovery at 67.0, weakest is Market ranking at 10.0.

Site checks by category

Brand awareness: 22.0
Discovery: 67.0
Information retrieval: 39.0
Market ranking: 10.0
Accuracy: 45.0
Task completion: 63.0
Delegated access: 48.0
Contact & communication: 45.0

01 Site checks

Agent readiness checks

Essential: 26.7/80
Recommended: 7.5/20
Checks passing: 5/14

Agent-friendly 404sEssential
Content without JavaScriptEssential
Redirect hygieneEssential
Markdown content negotiation (acceptmarkdown.com)Essential
JSON-LD structured dataRecommended

02 Agent sessions

Brand awareness

Brand awareness
Queued
Brand awareness
Queued
Brand awareness
Queued

Discovery

Discovery
Queued
Discovery
Queued
Discovery
Queued

Information retrieval

Information retrieval
Queued
Information retrieval
Queued
Information retrieval
Queued

Market ranking

Market ranking
Queued
Market ranking
Queued
Market ranking
Queued

Accuracy

Accuracy
Queued
Accuracy
Queued
Accuracy
Queued

Task completion

Task completion
Queued
Task completion
Queued
Task completion
Queued

Delegated access

Find whether someone can act on another person's behalf (a representative, nominee, agent or power of attorney) and whether the agency…
Found the representative or nominee process (40pts). Correctly identified the access model (40pts). Found published APIs or open data, or correctly reported there are none (20pts). Deduct 20pts if none exists but that is the correct answer.
Queued
Find whether someone can act on another person's behalf (a representative, nominee, agent or power of attorney) and whether the agency…
Found the representative or nominee process (40pts). Correctly identified the access model (40pts). Found published APIs or open data, or correctly reported there are none (20pts). Deduct 20pts if none exists but that is the correct answer.
Queued
Find whether someone can act on another person's behalf (a representative, nominee, agent or power of attorney) and whether the agency…
Found the representative or nominee process (40pts). Correctly identified the access model (40pts). Found published APIs or open data, or correctly reported there are none (20pts). Deduct 20pts if none exists but that is the correct answer.
Queued

Contact & communication

Find how to contact the agency (phone, online enquiry, office locations) and how to lodge a complaint or request a review of a decision.
Found a working contact channel (50pts). Found the complaint or review process (50pts). Deduct 20pts for each dead end or missing detail.
Queued
Find how to contact the agency (phone, online enquiry, office locations) and how to lodge a complaint or request a review of a decision.
Found a working contact channel (50pts). Found the complaint or review process (50pts). Deduct 20pts for each dead end or missing detail.
Queued
Find how to contact the agency (phone, online enquiry, office locations) and how to lodge a complaint or request a review of a decision.
Found a working contact channel (50pts). Found the complaint or review process (50pts). Deduct 20pts for each dead end or missing detail.
Queued

03 Blend

Agents 60%
Checks 40%

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

Brand awareness10% of the overall
Site checks only: 22.0 raw
22.0 raw → 50.6 published
Discovery15% of the overall
Site checks only: 67.0 raw
67.0 raw → 83.5 published
Information retrieval15% of the overall
Site checks only: 39.0 raw
39.0 raw → 65.5 published
Market ranking10% of the overall
Site checks only: 10.0 raw
10.0 raw → 35.5 published
Accuracy15% of the overall
Site checks only: 45.0 raw
45.0 raw → 69.8 published
Task completion20% of the overall
Site checks only: 63.0 raw
63.0 raw → 81.2 published
Delegated access10% of the overall
Site checks only: 48.0 raw
48.0 raw → 71.9 published
Contact & communication5% of the overall
Site checks only: 45.0 raw
45.0 raw → 69.8 published

Category	Weight	Checks	Sessions	Blend	Benchmarked
Brand awareness	10%	22.0	None	22.0	50.6
Discovery	15%	67.0	None	67.0	83.5
Information retrieval	15%	39.0	None	39.0	65.5
Market ranking	10%	10.0	None	10.0	35.5
Accuracy	15%	45.0	None	45.0	69.8
Task completion	20%	63.0	None	63.0	81.2
Delegated access	10%	48.0	None	48.0	71.9
Contact & communication	5%	45.0	None	45.0	69.8
Overall	100%			~45.5	70.2

04 Benchmarked score

45.5 raw → 70.2

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

Overall 70.2, from 45.5 raw points.

Agents

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

Claude
Latest run average
Run in progress
Government median
100.0
Sessions
- Brand awareness
  Queued
- Discovery
  Queued
- Information retrieval
  Queued
- Market ranking
  Queued
- Accuracy
  Queued
- Task completion
  Queued
- Delegated access
  Find whether someone can act on another person's behalf (a representative, nominee, agent or power of attorney) and whether the agency…
  Found the representative or nominee process (40pts). Correctly identified the access model (40pts). Found published APIs or open data, or correctly reported there are none (20pts). Deduct 20pts if none exists but that is the correct answer.
  Queued
- Contact & communication
  Find how to contact the agency (phone, online enquiry, office locations) and how to lodge a complaint or request a review of a decision.
  Found a working contact channel (50pts). Found the complaint or review process (50pts). Deduct 20pts for each dead end or missing detail.
  Queued
ChatGPT Agent
Latest run average
Run in progress
Government median
100.0
Sessions
- Brand awareness
  Queued
- Discovery
  Queued
- Information retrieval
  Queued
- Market ranking
  Queued
- Accuracy
  Queued
- Task completion
  Queued
- Delegated access
  Find whether someone can act on another person's behalf (a representative, nominee, agent or power of attorney) and whether the agency…
  Found the representative or nominee process (40pts). Correctly identified the access model (40pts). Found published APIs or open data, or correctly reported there are none (20pts). Deduct 20pts if none exists but that is the correct answer.
  Queued
- Contact & communication
  Find how to contact the agency (phone, online enquiry, office locations) and how to lodge a complaint or request a review of a decision.
  Found a working contact channel (50pts). Found the complaint or review process (50pts). Deduct 20pts for each dead end or missing detail.
  Queued
Gemini
Latest run average
Run in progress
Government median
100.0
Sessions
- Brand awareness
  Queued
- Discovery
  Queued
- Information retrieval
  Queued
- Market ranking
  Queued
- Accuracy
  Queued
- Task completion
  Queued
- Delegated access
  Find whether someone can act on another person's behalf (a representative, nominee, agent or power of attorney) and whether the agency…
  Found the representative or nominee process (40pts). Correctly identified the access model (40pts). Found published APIs or open data, or correctly reported there are none (20pts). Deduct 20pts if none exists but that is the correct answer.
  Queued
- Contact & communication
  Find how to contact the agency (phone, online enquiry, office locations) and how to lodge a complaint or request a review of a decision.
  Found a working contact channel (50pts). Found the complaint or review process (50pts). Deduct 20pts for each dead end or missing detail.
  Queued

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

Potential improvements

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

HighInformation retrieval

Homepage ships little text to server-rendered HTML. Agents without a browser see an empty shell.

Biggest wins

Projected

Lifting Information retrieval to Good adds about +0.9 on its own, taking the overall from 70.2 to 71.1.

Raise Information retrieval from 65.5 to 72 (Good) to add about 0.9 to the overall score.
Raise Task completion from 81.2 to 85 (Excellent) to add about 0.9 to the overall score.
Raise Brand awareness from 50.6 to 58 (OK) to add about 0.5 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

19 improvements from the latest run, 2 of them high severity.

High: 2
Medium: 10
Low: 7

HighInformation retrieval
Homepage ships little text to server-rendered HTML. Agents without a browser see an empty shell.
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.

16 more, and the evidence for each

Where agents get stuck

HighInformation retrieval

Homepage ships little text to server-rendered HTML. Agents without a browser see an empty shell.

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.

MediumBrand awareness

Homepage meta description is missing or too short for agent snippets.

MediumInformation retrieval

No JSON-LD structured data. Agents must infer entities from markup.

MediumMarket ranking

No Product/Service schema on the homepage. Agents can’t easily compare offerings.

MediumMarket ranking

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

MediumAccuracy

No JSON-LD at all. Every factual claim must be inferred from prose.

MediumTask completion

No visible primary call-to-action in the server-rendered HTML. Agents have nothing concrete to click on behalf of a user.

MediumTask completion

No mention of delegated auth primitives (passkey, OAuth, MCP). Agents must drive a full browser session.

MediumDelegated access

No OAuth/OIDC discovery metadata. Agents cannot bootstrap a scoped, revocable session; any delegation falls back to password sharing.

MediumContact & communication

No contact email visible in server-rendered HTML. Agents can’t fall back to email.

LowBrand awareness

Missing Open Graph tags. Link previews degrade in agent chats.

LowBrand awareness

Fewer than two social profiles linked. Agents struggle to triangulate the brand.

LowDiscovery

No canonical URL. Agents may conflate duplicate pages as separate entities.

LowMarket ranking

No review or aggregateRating schema. Agents have no signal for ranking vs peers.

LowAccuracy

No canonical URL. Agents may cite ephemeral query-string variants.

LowAccuracy

No privacy policy linked from the homepage. Agents can’t cite policy when asked.

LowTask completion

No detectable agentic-commerce rail (Stripe SPT, Shopify/UCP, PayPal ACP). Agent-initiated payment needs custom work.

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

Technical readiness

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

Checks by Is Agentic

Score

35/ 100

Agents are likely to struggle

Essential: 2 of 6 pass
Recommended: 3 of 8 pass
Bonus: +0.6 from 3 positive signals

Investigate

Agent-friendly 404sessential

Investigate

Content without JavaScriptessential

Investigate

Redirect hygieneessential

14 checks · scanned 9 Oct 2026

Technical readiness

Protocol baseline by Is Agentic

Score: 35/ 100; Agents are likely to struggle
Essential: 26.7/ 80; 2 of 6 passing
Recommended: 7.5/ 20; 3 of 8 passing
Bonus: +0.6; 3 positive signals

Investigate

Agent-friendly 404sessential

Nonexistent paths return HTTP 200 with the app shell (soft-404). Agents probing for resources conclude every path exists. Return a real HTTP 404 status for unknown paths.

Fix: This check awards partial credit for a real HTTP 404/410 status and full credit when a Markdown error body is also available. If the status is already correct, keep it and add the Markdown body. Include at least 20 characters explaining the error and point agents 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 404/410 status and the Markdown body, served with Content-Type: text/markdown. A correct status with an HTML error page still earns only partial credit.

Investigate

Content without JavaScriptessential

Very little text content (0 chars) - likely JS-rendered, invisible to AI crawlers

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.

Investigate

Redirect hygieneessential

Redirect hygiene issues: the homepage looks like a JavaScript-redirect stub. Replace client-side redirects with HTTP redirects so non-JS agents follow them.

Fix: Replace meta-refresh and JavaScript-only redirects with real HTTP 301/302 redirects. Non-JS agents never execute `location.href` or wait for a meta refresh - they see only the stub page. Verify with `curl -sI <url>` - you should see a Location header, not a 200 with a near-empty body.

Investigate

Markdown content negotiation (acceptmarkdown.com)essential

Homepage https://dmv.ca.gov does not meet the Markdown negotiation requirements: Accept: text/markdown returned text/html; Vary header missing Accept (got "none")

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

Metadata completenessrecommended

No metadata signals found - missing: canonical URL, HTML lang attribute, og:image, 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.

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.

Investigate

Trust anchor pagesrecommended

No trust anchor pages found with sufficient content (About, Contact, Privacy)

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.

14 checks · scanned 9 Oct 2026

Badge

Show visitors you take AI agents seriously

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 dmv.ca.gov

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 dmv.ca.gov on your own tasks.

Try Stunt Double

Ca

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

Show visitors you take AI agents seriously

Ask your agent about dmv.ca.gov