last9.io
success
Claude Code
intent
What does last9.io do and who is it for? Explain it back to me.
12steps
59.1sduration
$0.1493cost
108,327tokens
14 steps2 reasoning steps3 searches
home
docs
docs
docs
llms.txt
search
llms-full.txt
search
/product
docs
search
/features
100%
on-site discovery
89%
reliability
78%
link following
path origin
- previous resource78%
- prior knowledge22%
insight
The agent assembled a comprehensive explanation of Last9 by combining direct homepage/docs fetches with machine-readable artifact files (llms.txt and llms-full.txt). The site's structured content and documentation were accessible, but pricing details required inference from metadata and policy statements rather than explicit dollar amounts. The agent successfully answered what Last9 does, who it's for, and how it differs from alternatives, though pricing specifics remained gated behind a sales funnel.
- ›Steps [1], [4], [9], and [11] were the core content sources: [1] homepage provided the value proposition and meta description; [4] docs introduction explained technical positioning; [9] and [11] (llms.txt and llms-full.txt) supplied structured feature lists, integration details, and AI-native capabilities. These four steps contained 90% of the substantive answer.
- ›The site does NOT publish specific pricing numbers publicly—step [2] and [8] fetches of /pricing returned the same homepage HTML as step [1], indicating the pricing page is either JavaScript-rendered or gated. The agent inferred pricing structure (usage-based, volume discounts, Enterprise custom) from metadata descriptions and documentation fragments, not from an actual pricing table or calculator.
- ›Last9 publishes machine-readable summaries (llms.txt and llms-full.txt) that significantly accelerated identity comprehension. These artifacts encoded the product overview, integrations, deployment modes, and certifications in a compact, structured format—indicating the site is intentionally optimized for agent traversal.
- ›Competitor comparisons were discovered via web search (step [6], [10], [12]) pointing to blog articles, not a built-in comparison matrix on the main site. The agent had to cross-reference blog content to establish differentiation, rather than finding a structured alternative-vs-Last9 resource.
- ›The agent identified three significant friction points: (a) no public pricing calculator or dollar amounts, (b) single-page app routing preventing direct content fetch from /pricing and /features URLs (returned homepage HTML instead), and (c) unclear free trial / freemium availability despite thorough navigation.
Want to run your own?
Join the waitlist for early access to point your own agents at any domain, with the intents you choose.
or talk to us about agent readiness →