try.no
success
Claude Code
intent
What does try.no do and who is it for? Explain it back to me.
15steps
69.4sduration
$1.6602cost
186,181tokens
17 steps2 reasoning steps7 searches
home
/om-oss
/tjenester
/priser
/kontakt
/portfolio
search
/en/about-us
/en
search
search
search
search
search
search
75%
on-site discovery
75%
reliability
25%
link following
path origin
- previous resource25%
- web search25%
- prior knowledge50%
insight
The agent successfully assembled a comprehensive overview of try.no by combining site navigation (homepage, about, services pages) with web search results, but had to work around significant gaps in the site's own information architecture. Pricing was completely absent from the website, and service divisions were scattered across pages rather than clearly explained. The site is navigable but fragmented—the agent relied heavily on prior knowledge and search to fill in what the domain itself did not surface clearly.
- ›Steps [1], [2], [3], [8], [9] returned HTML with meta descriptions and page structure but minimal actual content detail in the truncated responses. The agent extracted positioning ('one roof'), division names (TRY Dig, TRY Studio, TRY Råd), and high-level messaging about integrated communication, but had to piece together the full service list from multiple page visits and search context.
- ›The site does not publish pricing or clear service/division explanations in fetchable form—step [4] hit a 404 on /priser (pricing), and steps [2], [3], [8], [9] show the site uses primarily visual/JavaScript-heavy pages that don't surface structural information in meta tags or plain HTML. The agent had to rely on web search (steps [7], [10], [12], [14], [15]) to find external validation (PRovoke Media, Semrush, LinkedIn, Sortlist) rather than internal documentation.
- ›The agent correctly identified gaps and called them out explicitly (no pricing, unclear division coordination, weak 'one roof' value prop explanation). This reflects accurate diagnosis of the site's agent-readiness: the domain is brand-first and lacks structured, machine-readable service/pricing data. The 'succeeded_with_heavy_bridge' friction outcome is justified—the agent bridged site gaps with 75% web search and prior knowledge sourcing.
- ›Steps [8] and [9] (English-language versions) were fetched after search results suggested them, indicating the agent had to discover the English portal via external search rather than site navigation—the Norwegian homepage did not expose language switching in the truncated response.
Help the next agent finish on try.no
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 →