Bolt

Name: Bolt AI agent readiness scorecard
Item: Bolt
Rating: 73.5
Author: Stunt Double

Get a ride in minutes, order food and grocery delivery, rent a car or scooter, improve business travel and more. Available in 850+ cities and 50+ countries.

bolt.eu
AudienceB2B
MarketsGB, AE, MA, SA, AZ, BG, ES, CZ
Localesen-GB, ar-AE, ar-MA, ar-SA, az-AZ, bg-BG, ca-ES, cs-CZ

Agent score25.4

/100Good

Claim this domain

RankRank: Top 71%; #392
Finance rankFinance rank: Sector average 79.6; #45
Benchmark runsBenchmark runs: 3 providersAcross 3 providers; 5

Where this site sits

Finance avg: 79.6 (−6.1)
Market avg: 76.7 (−3.2)

Latest results

Bolt ranks #392 of 550 scored sites, up 126 places since the last run.

Trend-6.2Since 14 May 2026, across 3 runs.Best agent100.0 ExcellentClaude. Gemini trails at 100.0.Agent friction8improvements1 high severity. Most serious: No contact page linked or reachable. Agents acting on a user’s behalf have nowhere to send a message.Technical readiness66/1004 of 8 essential checks failing.Checks by Is Agentic

This site
Finance
Market

Table view

Run	This site	Finance median	Market median
12 Oct 2026	73.5	81.0	79.8
28 Sept 2026	48.1	80.1	76.4
14 May 2026	79.7	80.5	82.0

Monthly medians. Dates in UTC.

Performance

Site checks, then AI agents on real tasks.

Methodology

Automated checks probe the site before any agent runs. They count for 40% of each category. Strongest is Accuracy at 100.0, weakest is Market ranking at 35.0.

Site checks by category

Brand awareness: 84.0
Discovery: 74.0
Information retrieval: 84.0
Market ranking: 35.0
Accuracy: 100.0
Task completion: 60.0
Contact & communication: 45.0

01 Site checks

Points by category

Brand awareness84.0
Discovery74.0
Information retrieval84.0
Market ranking35.0
Accuracy100.0
Task completion60.0
Contact & communication45.0

Agent readiness checks

Essential: 51.7/80
Recommended: 12.4/20
Checks passing: 11/22

OpenAPI spec publishedEssential
Markdown content negotiation (acceptmarkdown.com)Essential
CLI tool availableRecommended
Agent instruction / when-to-useRecommended
API schema complexity analysisRecommended

02 Agent sessions

Brand awareness

Brand awareness
1m 7s
17median 94
Brand awareness
1m 23s
65median 94
Brand awareness
1m 35s
32median 94

Discovery

Discovery
1m 41s
32median 73
Discovery
1m 58s
26median 73
Discovery
2m 30s
32median 73

Information retrieval

Information retrieval
1m 29s
78median 60
Information retrieval
2m 2s
36median 60
Information retrieval
2m 17s
21median 60

Market ranking

Market ranking
21s
43median 65
Market ranking
29s
43median 65
Market ranking
1m 54s
43median 65

Accuracy

Accuracy
22s
49median 87
Accuracy
1m 23s
46median 87
Accuracy
1m 45s
88median 87

Task completion

Task completion
50s
92median 89
Task completion
1m 36s
96median 89
Task completion
2m 4s
89median 89

Contact & communication

Find out how to close an account or transfer funds out.
Found the account closure or fund transfer process (50pts). Correctly described the steps and any applicable fees (50pts). Deduct 20pts for each dead end or missing detail.
1m 25s
89median 80
Find out how to close an account or transfer funds out.
Found the account closure or fund transfer process (50pts). Correctly described the steps and any applicable fees (50pts). Deduct 20pts for each dead end or missing detail.
3m 31s
58median 80
Find out how to close an account or transfer funds out.
Found the account closure or fund transfer process (50pts). Correctly described the steps and any applicable fees (50pts). Deduct 20pts for each dead end or missing detail.
3m 46s
56median 80

03 Blend

Agents 60%
Checks 40%

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

Brand awareness11% of the overall
0.4 × 84.0 + 0.6 × 16.0 = 43.2 raw
43.2 raw → 68.5 published
Discovery17% of the overall
0.4 × 74.0 + 0.6 × 7.0 = 33.8 raw
33.8 raw → 61.4 published
Information retrieval17% of the overall
0.4 × 84.0 + 0.6 × 23.7 = 47.8 raw
47.8 raw → 71.7 published
Market ranking11% of the overall
0.4 × 35.0 + 0.6 × 15.0 = 23.0 raw
23.0 raw → 51.6 published
Accuracy17% of the overall
0.4 × 100.0 + 0.6 × 37.7 = 62.6 raw
62.6 raw → 81.0 published
Task completion22% of the overall
0.4 × 60.0 + 0.6 × 84.0 = 74.4 raw
74.4 raw → 87.5 published
Contact & communication6% of the overall
0.4 × 45.0 + 0.6 × 45.3 = 45.2 raw
45.2 raw → 70.0 published

Category	Weight	Checks	Sessions	Blend	Benchmarked
Brand awareness	10%	84.0	16.0	43.2	68.5
Discovery	15%	74.0	7.0	33.8	61.4
Information retrieval	15%	84.0	23.7	47.8	71.7
Market ranking	10%	35.0	15.0	23.0	51.6
Accuracy	15%	100.0	37.7	62.6	81.0
Task completion	20%	60.0	84.0	74.4	87.5
Delegated access	10%	N/A
Contact & communication	5%	45.0	45.3	45.2	70.0
Overall	100%			~50.4	73.5

04 Benchmarked score

50.4 raw → 73.5

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 73.5, from 50.4 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
64.4
Finance median
100.0
Sessions
- Brand awareness
  1m 7s
  17median 94
- Discovery
  1m 41s
  32median 73
- Information retrieval
  1m 29s
  78median 60
- Market ranking
  21s
  43median 65
- Accuracy
  22s
  49median 87
- Task completion
  50s
  92median 89
- Contact & communication
  Find out how to close an account or transfer funds out.
  Found the account closure or fund transfer process (50pts). Correctly described the steps and any applicable fees (50pts). Deduct 20pts for each dead end or missing detail.
  1m 25s
  89median 80
ChatGPT Agent
Latest run average
57.9
Finance median
100.0
Sessions
- Brand awareness
  1m 23s
  65median 94
- Discovery
  1m 58s
  26median 73
- Information retrieval
  2m 2s
  36median 60
- Market ranking
  29s
  43median 65
- Accuracy
  1m 23s
  46median 87
- Task completion
  1m 36s
  96median 89
- Contact & communication
  Find out how to close an account or transfer funds out.
  Found the account closure or fund transfer process (50pts). Correctly described the steps and any applicable fees (50pts). Deduct 20pts for each dead end or missing detail.
  3m 31s
  58median 80
Gemini
Latest run average
58.8
Finance median
100.0
Sessions
- Brand awareness
  1m 35s
  32median 94
- Discovery
  2m 30s
  32median 73
- Information retrieval
  2m 17s
  21median 60
- Market ranking
  1m 54s
  43median 65
- Accuracy
  1m 45s
  88median 87
- Task completion
  2m 4s
  89median 89
- Contact & communication
  Find out how to close an account or transfer funds out.
  Found the account closure or fund transfer process (50pts). Correctly described the steps and any applicable fees (50pts). Deduct 20pts for each dead end or missing detail.
  3m 46s
  56median 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.

HighContact & communication

No contact page linked or reachable. Agents acting on a user’s behalf have nowhere to send a message.

Biggest wins

Projected

Lifting Discovery to Good adds about +1.5 on its own, taking the overall from 73.5 to 75.0.

Raise Discovery from 61.4 to 72 (Good) to add about 1.5 to the overall score.
Raise Accuracy from 81.0 to 85 (Excellent) to add about 0.7 to the overall score.
Raise Market ranking from 51.6 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

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

High: 1
Medium: 4
Low: 3

HighContact & communication
No contact page linked or reachable. Agents acting on a user’s behalf have nowhere to send a message.
MediumBrand awareness
No Organization JSON-LD. Agents can’t tell who owns the site at a glance.
MediumMarket ranking
No Product/Service schema on the homepage. Agents can’t easily compare offerings.

5 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

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

Checks by Is Agentic

Score

66/ 100

Important blockers remain

Essential: 4 of 8 pass
Recommended: 7 of 14 pass
Bonus: +2.1 from 10 positive signals

Investigate

OpenAPI spec publishedessential

Investigate

Markdown content negotiation (acceptmarkdown.com)essential

Investigate

CLI tool availablerecommended

22 checks · scanned 9 Oct 2026

Technical readiness

Protocol baseline by Is Agentic

Score: 66/ 100; Important blockers remain
Essential: 51.7/ 80; 4 of 8 passing
Recommended: 12.4/ 20; 7 of 14 passing
Bonus: +2.1; 10 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

Markdown content negotiation (acceptmarkdown.com)essential

Homepage https://bolt.eu 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-action, accept-encoding, origin")

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

Agent instruction / when-to-userecommended

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

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

Investigate

API schema complexity analysisrecommended

No API schema detected

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

Investigate

Function calling compatibilityrecommended

No API spec found - function calling requires discoverable endpoints

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

Partial

Agent-friendly 404sessential

The nonexistent path https://bolt.eu/__ora-404-probe-tel7vck9 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

3020 chars with H1, but 3.9% 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

Public API with reachable endpointsrecommended

Documentation site found at https://developer.bolt.eu but API content unclear. Best-of-protocols score: 3/7.

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

Partial

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

JSON-LD structured datarecommended

JSON-LD Person found - missing description, url, and one of sameAs / jobTitle / worksFor on this entity

Fix: Add description, url, and one of sameAs / jobTitle / worksFor to the Person JSON-LD entity for full score.

22 checks · scanned 9 Oct 2026

Opportunity cost · finance

Bolt could see ~$45,050,000 of processed value exposed to agent-led journeys each year

Gap to leader: 26.5 pts
Below finance avg: 3.2 pts
Modeled flows at risk: $45,050,000

Claim Bolt to use your own processed value

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 bolt.eu

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 bolt.eu on your own tasks.

Try Stunt Double

Bolt

By category

Points by category

Agent readiness checks

Brand awareness

Discovery

Information retrieval

Market ranking

Accuracy

Task completion

Contact & communication

Category weights

Agents

Sessions

Sessions

Sessions

Bolt could see ~$45,050,000 of processed value exposed to agent-led journeys each year

Show visitors your Good agent score

Ask your agent about bolt.eu