Show HN: Search for AI-agents and usefulness score
TL;DR
A team on Hacker News has launched a search engine built for AI agents that attaches a usefulness score and a price to every result page. The idea came from testing agents that research companies for sales outreach: in four out of seven cases they produced outdated insights even when recent news was in their context, and a larger model did not fix it. The score is meant to cut token use and cost by letting agents read only relevant pages, while improving answer quality.
Nauti's Take
The potential is practical: if agents read only the most relevant pages, token costs fall and outdated results carry less weight. The limit is the score itself, since it remains unclear how it is calculated and whether it holds up on niche topics.
Teams running research agents can test the tool alongside their current search and compare freshness and cost directly.
Video
Sources