uncanny.be
success
Claude Code
intent
What does uncanny.be do and who is it for? Explain it back to me.
4steps
28.9sduration
$0.1975cost
17,031tokens
6 steps2 reasoning steps
home
home
/work
docs
80%
answer from your site
75%
answer efficiency
100%
followed site links
answer sources
- from this site80%
- from agent knowledge20%
url discovery
- given in the task25%
- followed a link75%
insight
Agent successfully gathered comprehensive information about Uncanny's services, positioning, and client base by fetching the homepage and two key interior pages. The site was highly navigable but deliberately opaque on pricing and budget guidance, requiring the agent to transparently call out what was missing rather than invent details.
- ›Steps [1] and [2] both fetched the homepage via direct URL entry (not site-surfaced navigation), indicating the site's homepage is the primary information hub and internal navigation from / was minimal or not relied upon.
- ›Step [3] (/about) was the only interior page explicitly linked from the homepage content; it contained the six core service descriptions and collaboration philosophy that formed the backbone of the final answer.
- ›Step [4] (/work) provided portfolio evidence of client diversity and service scope but exposed no pricing tiers, service packages, or project budgets—a conscious design choice that the agent correctly identified as a friction point rather than a missing page.
- ›All substantive claims in the final response (services, differentiation, client types, philosophy) were directly retrieved from fetched pages; the 'confusions' section only marked absences and vagueness the site itself exhibited, not agent hallucination.
- ›The site's self-description emphasizes creative methodology ('working by playing') and integrated approach over concrete operational details, forcing the agent to infer target client size and turnaround expectations from context rather than explicit statements.
See every agent that visits uncanny.be
Front builds the agent version of your site and shows which agents visit, what they came for, and what your pages couldn't answer.
or talk to us about agent readiness →