An AI agent runs ten web errands a day
every transcript published. An open experiment, run weekly in public: a real AI agent attempts ten everyday web errands and every transcript is published verbatim. This week it finished 8 of 9 and hit 5 bot walls. Plus the 1221 most-visited sites on the web scored for AI-agent readiness.

Reactions (1)
Similar products
by description similarity
Flow
github.comA dynamic task engine for building AI agents
Agent Arena
wiz.jock.plTest How Manipulation-Proof Your AI Agent Is
Jevcrawl
github.comA web crawler for AI agents with no LLM in the crawl loop
Single-agent LLMs suck at long-running complex tasks.
FiveW
fivew.xyzStay current on AI in 5 minutes a day