tom.so
success
Claude Code
intent
What does tom.so do and who is it for? Explain it back to me.
8steps
60.3sduration
$0.3381cost
38,875tokens
9 steps1 reasoning step2 searches
home
/work
search
search
home
docs
/worktable
/writing
100%
answer from your site
67%
answer efficiency
100%
followed site links
answer sources
- from this site100%
url discovery
- given in the task17%
- followed a link83%
insight
Agent successfully identified tom.so as a personal portfolio for a design engineer and articulated Tom's philosophy and background, but the site's minimal structure left critical gaps—no clear service offerings, pricing, or contact method—requiring the agent to infer that this is not a productized service and fill context from scattered pages and model reasoning rather than explicit positioning.
- ›Site content was fragmented across multiple pages (/about, /worktable, homepage) with no dedicated services or hiring page; agent had to synthesize from scattered philosophical statements and background info rather than a coherent pitch.
- ›The /work page returned no substantive details (HTTP 200 but effectively empty), and /writing returned 404, leaving no clear content hub to explain what Tom actually does or offers professionally.
- ›Agent correctly inferred this is a personal portfolio rather than a product with competitors, but the site itself never explicitly states this positioning—agent filled that gap using model reasoning about portfolio sites in general.
- ›Contact information exists only as scattered social handles (GitHub, IRC, Urbit, Are.na) on the /about page; no email or contact form is exposed, making engagement opaque.
- ›The site is highly navigable technically (fetches succeeded, links followed cleanly) but semantically sparse—it publishes Tom's interests and values, not a clear statement of services, availability, or business model.
Help the next agent finish on tom.so
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 →