Automated checks probe the site before any agent runs. They count for 40% of each category. Strongest is Discovery at 75.0, weakest is Delegated access at 0.0.
Site checks by category
Brand awareness
50.0
Discovery
75.0
Information retrieval
65.0
Market ranking
45.0
Accuracy
70.0
Task completion
65.0
Delegated access
0.0
Contact & communication
10.0
01 Site checks
Points by category
Brand awareness
50.0
Discovery
75.0
Information retrieval
65.0
Market ranking
45.0
Accuracy
70.0
Task completion
65.0
Delegated access
0.0
Contact & communication
10.0
02 Agent sessions
Brand awareness
Find the firm name, the services it offers, and the kind of client it targets (startup, enterprise, public sector, consumers).
Firm name (30pts), services offered (40pts), target client (30pts). Deduct 20pts for hallucinations.
1m 26s
85median 91
Find the firm name, the services it offers, and the kind of client it targets (startup, enterprise, public sector, consumers).
Firm name (30pts), services offered (40pts), target client (30pts). Deduct 20pts for hallucinations.
6m 13s
86median 91
Find the firm name, the services it offers, and the kind of client it targets (startup, enterprise, public sector, consumers).
Firm name (30pts), services offered (40pts), target client (30pts). Deduct 20pts for hallucinations.
10m 37s
76median 91
Find the firm name, the services it offers, and the kind of client it targets (startup, enterprise, public sector, consumers).
Firm name (30pts), services offered (40pts), target client (30pts). Deduct 20pts for hallucinations.
4m 54s
26median 91
Discovery
Navigate to the services or capabilities page, and note its URL and the service areas listed.
Found the services/capabilities page within 3 nav hops (60pts). Correctly listed at least two service areas (40pts). Deduct 20pts for each dead end.
50s
90median 80
Navigate to the services or capabilities page, and note its URL and the service areas listed.
Found the services/capabilities page within 3 nav hops (60pts). Correctly listed at least two service areas (40pts). Deduct 20pts for each dead end.
2m 50s
95median 80
Navigate to the services or capabilities page, and note its URL and the service areas listed.
Found the services/capabilities page within 3 nav hops (60pts). Correctly listed at least two service areas (40pts). Deduct 20pts for each dead end.
4m 19s
36median 80
Navigate to the services or capabilities page, and note its URL and the service areas listed.
Found the services/capabilities page within 3 nav hops (60pts). Correctly listed at least two service areas (40pts). Deduct 20pts for each dead end.
2m 59s
36median 80
Information retrieval
Find the core service areas offered, one named client or case study, and how a prospective client starts an engagement (form, call…
Service areas (30pts), a named client or case study (30pts), the engagement path (30pts). Correct and sourced from the site (10pts). Deduct 20pts for any hallucinated data.
1m 27s
81median 77
Find the core service areas offered, one named client or case study, and how a prospective client starts an engagement (form, call…
Service areas (30pts), a named client or case study (30pts), the engagement path (30pts). Correct and sourced from the site (10pts). Deduct 20pts for any hallucinated data.
6m 15s
89median 77
Market ranking
Based on your knowledge, name 3 direct competitors to novabook.com in its professional-services niche and rank them by reputation or…
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 professional-services niche; cap the score at 40 if competitors are hallucinated or drawn from a different sector.
8s
36median 68
Based on your knowledge, name 3 direct competitors to novabook.com in its professional-services niche and rank them by reputation or…
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 professional-services niche; cap the score at 40 if competitors are hallucinated or drawn from a different sector.
9s
43median 68
Accuracy
Find out whether the firm publishes pricing, rates, or engagement models (fixed fee, retainer, time and materials), reporting exactly what…
Answered what pricing or engagement-model information is published (50pts). Answer was factually correct and sourced from the site, including correctly reporting absence (50pts). Deduct 40pts for invented rates or models.
1m 25s
89median 89
Find out whether the firm publishes pricing, rates, or engagement models (fixed fee, retainer, time and materials), reporting exactly what…
Answered what pricing or engagement-model information is published (50pts). Answer was factually correct and sourced from the site, including correctly reporting absence (50pts). Deduct 40pts for invented rates or models.
6m 12s
92median 89
Task completion
Find the primary call-to-action for starting an engagement (contact form, call booking, proposal request) and reach the form.
Found the primary CTA (20pts). Clicked through (20pts). Reached a working enquiry or booking form (40pts). Reported the URL and form fields (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit.
52s
99median 85
Find the primary call-to-action for starting an engagement (contact form, call booking, proposal request) and reach the form.
Found the primary CTA (20pts). Clicked through (20pts). Reached a working enquiry or booking form (40pts). Reported the URL and form fields (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit.
2m 52s
93median 85
Find the primary call-to-action for starting an engagement (contact form, call booking, proposal request) and reach the form.
Found the primary CTA (20pts). Clicked through (20pts). Reached a working enquiry or booking form (40pts). Reported the URL and form fields (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit.
4m 20s
54median 85
Find the primary call-to-action for starting an engagement (contact form, call booking, proposal request) and reach the form.
Found the primary CTA (20pts). Clicked through (20pts). Reached a working enquiry or booking form (40pts). Reported the URL and form fields (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit.
2m 59s
88median 85
03 Blend
Agents 60%
Checks 40%
One kind of evidence only? That kind counts in full.
Brand awareness10% of the overall
0.4 × 50.0 + 0.6 × 71.0 = 62.6 raw
62.6 raw → 81.0 published
Discovery15% of the overall
0.4 × 75.0 + 0.6 × 85.0 = 81.0 raw
81.0 raw → 91.0 published
Information retrieval15% of the overall
0.4 × 65.0 + 0.6 × 70.0 = 68.0 raw
68.0 raw → 84.1 published
Market ranking10% of the overall
0.4 × 45.0 + 0.6 × 12.5 = 25.5 raw
25.5 raw → 54.1 published
Accuracy15% of the overall
0.4 × 70.0 + 0.6 × 80.0 = 76.0 raw
76.0 raw → 88.4 published
Task completion20% of the overall
0.4 × 65.0 + 0.6 × 91.5 = 80.9 raw
80.9 raw → 90.9 published
Delegated access10% of the overall
Site checks only: 0.0 raw
0.0 raw → 0.0 published
Contact & communication5% of the overall
Site checks only: 10.0 raw
10.0 raw → 35.5 published
Category
Weight
Checks
Sessions
Blend
Benchmarked
Brand awareness
10%
50.0
71.0
62.6
81.0
Discovery
15%
75.0
85.0
81.0
91.0
Information retrieval
15%
65.0
70.0
68.0
84.1
Market ranking
10%
45.0
12.5
25.5
54.1
Accuracy
15%
70.0
80.0
76.0
88.4
Task completion
20%
65.0
91.5
80.9
90.9
Delegated access
10%
0.0
None
0.0
0.0
Contact & communication
5%
10.0
None
10.0
35.5
Overall
100%
~59.3
79.0
04 Benchmarked score
59.3 raw → 79.0
Final score is calibrated and adjusted to better reflect the actual performance and benchmark.
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 79.0, from 59.3 raw points.
Agents
Each agent’s score over 30 days, and how its latest sessions went.
Claude
Latest run average
83.1
Professional services median
95.3
Sessions
Brand awareness
Find the firm name, the services it offers, and the kind of client it targets (startup, enterprise, public sector, consumers).
Firm name (30pts), services offered (40pts), target client (30pts). Deduct 20pts for hallucinations.
1m 26s
85median 91
Discovery
Navigate to the services or capabilities page, and note its URL and the service areas listed.
Found the services/capabilities page within 3 nav hops (60pts). Correctly listed at least two service areas (40pts). Deduct 20pts for each dead end.
50s
90median 80
Information retrieval
Find the core service areas offered, one named client or case study, and how a prospective client starts an engagement (form, call…
Service areas (30pts), a named client or case study (30pts), the engagement path (30pts). Correct and sourced from the site (10pts). Deduct 20pts for any hallucinated data.
1m 27s
81median 77
Market ranking
Based on your knowledge, name 3 direct competitors to novabook.com in its professional-services niche and rank them by reputation or…
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 professional-services niche; cap the score at 40 if competitors are hallucinated or drawn from a different sector.
8s
36median 68
Accuracy
Find out whether the firm publishes pricing, rates, or engagement models (fixed fee, retainer, time and materials), reporting exactly what…
Answered what pricing or engagement-model information is published (50pts). Answer was factually correct and sourced from the site, including correctly reporting absence (50pts). Deduct 40pts for invented rates or models.
1m 25s
89median 89
Task completion
Find the primary call-to-action for starting an engagement (contact form, call booking, proposal request) and reach the form.
Found the primary CTA (20pts). Clicked through (20pts). Reached a working enquiry or booking form (40pts). Reported the URL and form fields (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit.
52s
99median 85
ChatGPT Agent
Latest run average
85.3
Professional services median
87.1
Sessions
Brand awareness
Find the firm name, the services it offers, and the kind of client it targets (startup, enterprise, public sector, consumers).
Firm name (30pts), services offered (40pts), target client (30pts). Deduct 20pts for hallucinations.
6m 13s
86median 91
Discovery
Navigate to the services or capabilities page, and note its URL and the service areas listed.
Found the services/capabilities page within 3 nav hops (60pts). Correctly listed at least two service areas (40pts). Deduct 20pts for each dead end.
2m 50s
95median 80
Information retrieval
Find the core service areas offered, one named client or case study, and how a prospective client starts an engagement (form, call…
Service areas (30pts), a named client or case study (30pts), the engagement path (30pts). Correct and sourced from the site (10pts). Deduct 20pts for any hallucinated data.
6m 15s
89median 77
Market ranking
Based on your knowledge, name 3 direct competitors to novabook.com in its professional-services niche and rank them by reputation or…
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 professional-services niche; cap the score at 40 if competitors are hallucinated or drawn from a different sector.
9s
43median 68
Accuracy
Find out whether the firm publishes pricing, rates, or engagement models (fixed fee, retainer, time and materials), reporting exactly what…
Answered what pricing or engagement-model information is published (50pts). Answer was factually correct and sourced from the site, including correctly reporting absence (50pts). Deduct 40pts for invented rates or models.
6m 12s
92median 89
Task completion
Find the primary call-to-action for starting an engagement (contact form, call booking, proposal request) and reach the form.
Found the primary CTA (20pts). Clicked through (20pts). Reached a working enquiry or booking form (40pts). Reported the URL and form fields (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit.
2m 52s
93median 85
Kimi
Latest run average
58.2
Professional services median
Too few sites yet for a median
Sessions
Brand awareness
Find the firm name, the services it offers, and the kind of client it targets (startup, enterprise, public sector, consumers).
Firm name (30pts), services offered (40pts), target client (30pts). Deduct 20pts for hallucinations.
10m 37s
76median 91
Discovery
Navigate to the services or capabilities page, and note its URL and the service areas listed.
Found the services/capabilities page within 3 nav hops (60pts). Correctly listed at least two service areas (40pts). Deduct 20pts for each dead end.
4m 19s
36median 80
Task completion
Find the primary call-to-action for starting an engagement (contact form, call booking, proposal request) and reach the form.
Found the primary CTA (20pts). Clicked through (20pts). Reached a working enquiry or booking form (40pts). Reported the URL and form fields (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit.
4m 20s
54median 85
Llama
Latest run average
58.2
Professional services median
Too few sites yet for a median
Sessions
Brand awareness
Find the firm name, the services it offers, and the kind of client it targets (startup, enterprise, public sector, consumers).
Firm name (30pts), services offered (40pts), target client (30pts). Deduct 20pts for hallucinations.
4m 54s
26median 91
Discovery
Navigate to the services or capabilities page, and note its URL and the service areas listed.
Found the services/capabilities page within 3 nav hops (60pts). Correctly listed at least two service areas (40pts). Deduct 20pts for each dead end.
2m 59s
36median 80
Task completion
Find the primary call-to-action for starting an engagement (contact form, call booking, proposal request) and reach the form.
Found the primary CTA (20pts). Clicked through (20pts). Reached a working enquiry or booking form (40pts). Reported the URL and form fields (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit.
2m 59s
88median 85
Excellent85+
Good72-84
OK58-71
Poor40-57
Critical<40
Latest run 1 Oct 2026 (UTC). Sign in to request a re-run from 2 Oct 2026, 11:03 UTC.
03 / 03
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 Delegated access to Poor adds about +0.8 on its own, taking the overall from 79.0 to 79.8.
Raise Delegated access from 0.0 to 40 (Poor) to add about 0.8 to the overall score.