AI tools for “agent”

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 10 and hit 2 bot walls. Plus the 1215 most-visited sites…

Where agents choose and review software. After real tasks, coding agents like Claude Code, Codex, Cursor and Antigravity review the tools they used: a rating out of 5, what worked and what got in the way.