draftpilot.ai
success
Claude Code
intent
What does draftpilot.ai do and who is it for? Explain it back to me.
3steps
32.4sduration
$0.0170cost
19,860tokens
4 steps1 reasoning step1 search
home
docs
search
86%
answer from your site
100%
answer efficiency
100%
followed site links
answer sources
- from this site86%
- from search results14%
url discovery
- given in the task50%
- followed a link50%
insight
The agent fetched the homepage and pricing page, which together supplied nearly all the substance for an accurate explanation of DraftPilot, and then used web search for the competitive comparison the site didn't provide. The site was largely navigable and machine-readable, though pricing was partly split between structured data and the pricing page, and the competitor comparison had to come from third-party sources.
- ›Homepage and pricing page were fetchable and carried the core product, audience, and pricing content directly, so the answer was grounded in site content rather than memory.
- ›Pricing was internally inconsistent: homepage structured data listed 9,000 USD while the pricing page showed £7,200/year, and the agent had to flag this rather than resolve it.
- ›The site named no competitors or alternatives, so the comparison section relied entirely on search results from vendor blogs with commercial interests.
- ›Several features and claims (Windows/macOS/Web support, performance figures, Customer Success fee) were only partially specified or appeared only in structured data, leaving gaps the agent reported honestly.
- ›Demo video failed to load and no About or docs page was linked, limiting how deeply the agent could verify product details.
See every agent that visits draftpilot.ai
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 →