Kubernetes
Kubernetes, also known as K8s, is an open source system for automating deployment, scaling, and management of containerized applications. It groups containers that make up an application into logical units for easy management and discovery. Kubernetes builds upon 15 years of experience of running production workload…
- kubernetes.io
- AudienceDeveloper
- Localeen
- Rank
- Top 48%
- #265
- Professional services rank
- Sector average 81.8
- #21
- Benchmark runs
- 3 providersAcross 3 providers
- 5
- Professional services avg
- 81.8 (−2.6)
- Market avg
- 76.7 (+2.5)
01
Latest results
Kubernetes ranks #265 of 550 scored sites, up 217 places since the last run.
- This site
- Professional services
- Market
By category
- Brand awareness88up 6.0
- Discovery85up 9.0
- Information retrieval76down 16.5
- Market ranking62up 19.7
- Accuracy89up 12.2
- Task completion72up 1.9
- Delegated access80up 79.9
- Contact & communication73up 47.2
Table view
Monthly medians. Dates in UTC.
02
Performance
Site checks, then AI agents on real tasks.
Automated checks probe the site before any agent runs. They count for 40% of each category. Strongest is Discovery at 77.0, weakest is Contact & communication at 5.0.
Site checks by category
- Brand awareness
- 66.0
- Discovery
- 77.0
- Information retrieval
- 74.0
- Market ranking
- 21.0
- Accuracy
- 55.0
- Task completion
- 60.0
- Delegated access
- 22.0
- Contact & communication
- 5.0
01 Site checks
Points by category
- Brand awareness66.0
- Discovery77.0
- Information retrieval74.0
- Market ranking21.0
- Accuracy55.0
- Task completion60.0
- Delegated access22.0
- Contact & communication5.0
Agent readiness checks
- Essential
- 41.7/80
- Recommended
- 12/20
- Checks passing
- 9/23
- OpenAPI spec publishedEssential
- JSON error responsesEssential
- Markdown content negotiation (acceptmarkdown.com)Essential
- Agent instruction / when-to-useRecommended
- API schema complexity analysisRecommended
02 Agent sessions
Brand awareness
Brand awareness
21s
89median 95Brand awareness
29s
96median 95Brand awareness
55s
89median 95
Discovery
Discovery
46s
93median 85Discovery
53s
93median 85Discovery
2m 27s
56median 85
Information retrieval
Information retrieval
48s
81median 91Information retrieval
1m 47s
81median 91Information retrieval
2m 22s
21median 91
Market ranking
Market ranking
22s
58median 68Market ranking
32s
43median 68Market ranking
25s
94median 68
Accuracy
Accuracy
26s
96median 91Accuracy
1m 56s
95median 91Accuracy
1m 4s
95median 91
Task completion
Task completion
1m 17s
81median 88Task completion
2m 9s
68median 88Task completion
4m 27s
43median 88
Delegated access
Find any client portal, partner programme, or API documentation.
Found a portal, partner programme, or API documentation (40pts). Correctly identified the access model (40pts). Named specific integration details (20pts). Deduct 20pts if none exists but that is the correct answer.
44s
89median 90Find any client portal, partner programme, or API documentation.
Found a portal, partner programme, or API documentation (40pts). Correctly identified the access model (40pts). Named specific integration details (20pts). Deduct 20pts if none exists but that is the correct answer.
3m 27s
98median 90
Contact & communication
Find how to contact the firm: channels available (email, phone, form), office locations, and any stated response expectations.
Found a working contact channel (50pts). Correctly reported locations and any response expectations (50pts). Deduct 20pts for each dead end or missing detail.
1m 16s
86median 85Find how to contact the firm: channels available (email, phone, form), office locations, and any stated response expectations.
Found a working contact channel (50pts). Correctly reported locations and any response expectations (50pts). Deduct 20pts for each dead end or missing detail.
2m 29s
94median 85
03 Blend
- Agents 60%
- Checks 40%
One kind of evidence only? That kind counts in full.
- Brand awareness10% of the overall0.4 × 66.0 + 0.6 × 82.7 = 76.0 raw76.0 raw → 88.4 published
- Discovery15% of the overall0.4 × 77.0 + 0.6 × 66.0 = 70.4 raw70.4 raw → 85.4 published
- Information retrieval15% of the overall0.4 × 74.0 + 0.6 × 42.3 = 55.0 raw55.0 raw → 76.4 published
- Market ranking10% of the overall0.4 × 21.0 + 0.6 × 44.3 = 35.0 raw35.0 raw → 62.3 published
- Accuracy15% of the overall0.4 × 55.0 + 0.6 × 90.7 = 76.4 raw76.4 raw → 88.6 published
- Task completion20% of the overall0.4 × 60.0 + 0.6 × 39.7 = 47.8 raw47.8 raw → 71.7 published
- Delegated access10% of the overall0.4 × 22.0 + 0.6 × 86.5 = 60.7 raw60.7 raw → 79.9 published
- Contact & communication5% of the overall0.4 × 5.0 + 0.6 × 80.0 = 50.0 raw50.0 raw → 73.2 published
04 Benchmarked score
59.5 raw → 79.2
Category weights
- Brand awareness 10%
- Discovery 15%
- Information retrieval 15%
- Market ranking 10%
- Accuracy 15%
- Task completion 20%
- Delegated access 10%
- Contact & communication 5%
Overall 79.2, from 59.5 raw points.
Agents
Each agent’s score over 30 days, and how its latest sessions went.
Claude
- Latest run average
- 85.0
- Professional services median
- 100.0
Sessions
Brand awareness
21s
89median 95Discovery
46s
93median 85Information retrieval
48s
81median 91Market ranking
22s
58median 68Accuracy
26s
96median 91Task completion
1m 17s
81median 88Delegated access
Find any client portal, partner programme, or API documentation.
Found a portal, partner programme, or API documentation (40pts). Correctly identified the access model (40pts). Named specific integration details (20pts). Deduct 20pts if none exists but that is the correct answer.
44s
89median 90
ChatGPT Agent
- Latest run average
- 82.6
- Professional services median
- 100.0
Sessions
Brand awareness
29s
96median 95Discovery
53s
93median 85Information retrieval
1m 47s
81median 91Market ranking
32s
43median 68Accuracy
1m 56s
95median 91Task completion
2m 9s
68median 88Contact & communication
Find how to contact the firm: channels available (email, phone, form), office locations, and any stated response expectations.
Found a working contact channel (50pts). Correctly reported locations and any response expectations (50pts). Deduct 20pts for each dead end or missing detail.
1m 16s
86median 85
Gemini
- Latest run average
- 79.8
- Professional services median
- 100.0
Sessions
Brand awareness
55s
89median 95Discovery
2m 27s
56median 85Information retrieval
2m 22s
21median 91Market ranking
25s
94median 68Accuracy
1m 4s
95median 91Task completion
4m 27s
43median 88Delegated access
Find any client portal, partner programme, or API documentation.
Found a portal, partner programme, or API documentation (40pts). Correctly identified the access model (40pts). Named specific integration details (20pts). Deduct 20pts if none exists but that is the correct answer.
3m 27s
98median 90Contact & communication
Find how to contact the firm: channels available (email, phone, form), office locations, and any stated response expectations.
Found a working contact channel (50pts). Correctly reported locations and any response expectations (50pts). Deduct 20pts for each dead end or missing detail.
2m 29s
94median 85
Latest run 12 Oct 2026 (UTC). Sign in to request a re-run, once a day.
03
Potential improvements
Fix where agents got stuck, then lift your biggest categories.
No discoverable MCP server. Agents and AI clients have no way to discover one automatically.
Biggest wins
Lifting Information retrieval to Excellent adds about +1.3 on its own, taking the overall from 79.2 to 80.5.
Raise Information retrieval from 76.4 to 85 (Excellent) to add about 1.3 to the overall score.
Raise Market ranking from 62.3 to 72 (Good) to add about 0.7 to the overall score.
Raise Contact & communication from 73.2 to 85 (Excellent) 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
17 improvements from the latest run, 3 of them high severity.
- High
- 3
- Medium
- 8
- Low
- 6
- HighDelegated access
No discoverable MCP server. Agents and AI clients have no way to discover one automatically.
- HighDelegated access
No discoverable public API docs. Agents and AI clients have no way to discover them automatically.
- HighContact & communication
No contact page linked or reachable. Agents acting on a user’s behalf have nowhere to send a message.
Where agents get stuck
No discoverable MCP server. Agents and AI clients have no way to discover one automatically.
No discoverable public API docs. Agents and AI clients have no way to discover them automatically.
No contact page linked or reachable. Agents acting on a user’s behalf have nowhere to send a message.
No Organization JSON-LD. Agents can’t tell who owns the site at a glance.
No JSON-LD structured data. Agents must infer entities from markup.
No Product/Service schema on the homepage. Agents can’t easily compare offerings.
No JSON-LD at all. Every factual claim must be inferred from prose.
The homepage has no link an agent can follow to start a task (pricing, sign-up, cart, booking). Links rendered only by JavaScript are invisible to agents that read the HTML.
No mention of delegated auth primitives (passkey, OAuth, MCP). Agents must drive a full browser session.
No OAuth/OIDC discovery metadata. Agents cannot bootstrap a scoped, revocable session; any delegation falls back to password sharing.
No contact email visible in server-rendered HTML. Agents can’t fall back to email.
No canonical URL. Agents may conflate duplicate pages as separate entities.
No review or aggregateRating schema. Agents have no signal for ranking vs peers.
No canonical URL. Agents may cite ephemeral query-string variants.
No privacy policy linked from the homepage. Agents can’t cite policy when asked.
No detectable agentic-commerce rail (Stripe SPT, Shopify/UCP, PayPal ACP). Agent-initiated payment needs custom work.
No help, support, or FAQ hub linked. Agents can’t self-serve an answer before reaching out.
Want to find these in your own flows before an agent does? Read how to test your product for AI agent users.
Technical readiness
5 of 8 essential checks fail. These are the files and signals agents read before they act.
Score
56/ 100
Important blockers remain
- Essential
- 3 of 8 pass
- Recommended
- 6 of 15 pass
- Bonus
- +2 from 9 positive signals
Technical readiness
Protocol baseline by Is Agentic
- Score
- 56/ 100
- Important blockers remain
- Essential
- 41.7/ 80
- 3 of 8 passing
- Recommended
- 12/ 20
- 6 of 15 passing
- Bonus
- +2
- 9 positive signals
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 kubernetes.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/indexDiscover more insights with Stunt Double
Send AI agents through kubernetes.io on your own tasks.