wordradar.dev
success
Claude Code
intent
What does wordradar.dev do and who is it for? Explain it back to me.
2steps
26.2sduration
$0.0035cost
13,590tokens
4 steps2 reasoning steps
home
docs
100%
answer from your site
100%
answer efficiency
100%
followed site links
answer sources
- from this site100%
url discovery
- given in the task50%
- followed a link50%
insight
Agent successfully gathered enough information to explain wordradar's purpose, features, pricing, and positioning, but the site left critical operational details undocumented—credit costs per endpoint, post-beta pricing, rate limits, and how to obtain invite codes. The agent had to retrieve two pages and flag gaps rather than fill them from memory.
- ›Homepage alone answered ~70% of the task (what it does, beta status, high-level pricing tiers), but required the /docs page to clarify free-tier credit amounts (50 + 5/day) and confirm that only one endpoint's credit cost was documented—a significant gap for comparing pack value.
- ›Site published no competitor names or direct comparisons, only generic claims ('incumbents gate at $199+/month')—the agent noted this lack of evidence clearly rather than inferring specifics from memory.
- ›Critical operational unknowns (credit costs for Proxy-KD, Domain Timeline, Trends; post-beta pricing; rate limits; invite code acquisition) were absent from both fetched pages, forcing the agent to highlight them as unresolved rather than speculate.
- ›MCP server URL uses www-prefixed domain (www.wordradar.dev/mcp) while homepage uses bare domain—a discrepancy the agent caught and flagged as a potential concern.
- ›Agent reached the docs page via a link on the homepage, confirming the site does surface its technical reference, but the docs were incomplete (credit costs, rate limits, data refresh details missing), making the site less agent-ready than its structure suggests.
Help the next agent finish on wordradar.dev
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 →