Agentability · an open experiment on the agentic web · a new episode every day
Can AI agents actually use the web?
We find out in public, every day. An AI producer reads what the world is searching that morning and turns it into ten real errands — what time is kick-off and on which channel, what magnitude was the quake, what does it cost, what actually happened — and a real AI agent attempts them using nothing but plain web requests: no logins, no JavaScript, no human help. Every transcript is published verbatim, wins and failures alike. Alongside the show, the 1219 most-visited sites on the web are scored on how usable they actually are for an agent.
Today's answer · episode of October 15, 2026
6 bot walls · 94 pages read · 31 sites visited
New here? Watch an agent try and fail · look up a site's score · fix your own site · take the raw data
Where it got interesting
The other half: the 1219 most-visited sites, scored
Every week the 1219 most-visited sites on the web are audited against the
conventions real AI agents rely on — llms.txt, crawler policy, content you can read without a browser,
structured data, MCP. Every site gets a public report with a score and the exact fix for each failed check. When the
agent hits a wall in an episode, the index has usually already predicted it.
Who is ready, and who is not
31 sites answer every check perfectly, so the top of the ranking is a 31-way tie and tells you nothing. The spread, and the bottom, do.
- 124 grade A
- 230 grade B
- 175 grade C
- 117 grade D
- 351 grade F
- 222 closed by policy
Perfect 100/100 — 31 sites
Where agents get stuck — ranks 1215–1219 of 1219
| # | Site | Score | Grade |
|---|---|---|---|
| 1215 | naver.com closed by policy | 0 | Closed by policy |
| 1216 | quora.com closed by policy | 0 | Closed by policy |
| 1217 | realestate.com.au closed by policy | 0 | Closed by policy |
| 1218 | wordreference.com closed by policy | 0 | Closed by policy |
| 1219 | yelp.com closed by policy | 0 | Closed by policy |
Full ranked index of 1219 sites →
Why this exists
Agents are the web's newest audience: assistants that read pages, cite sources, and run errands for people. Whether the web actually works for them is an empirical question — so we test it, in public, every week, with verbatim transcripts, reproducible checks, and open data. History accrues weekly (10 snapshots so far).