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 1215 most-visited sites on the web are scored on how usable they actually are for an agent.

Today's answer · episode of October 10, 2026

10/10

errands the agent actually finished

9 bot walls · 131 pages read · 47 sites visited

10 done

Read today's transcripts → See all 1215 site scores

New here? Watch an agent try and fail · look up a site's score · fix your own site · take the raw data

no retriesno editingno cherry-pickingread-only http get — no javascript, no logins, no formsagent: deepseek-flashproducer: deepseek-v4-pro + live searchevery transcript published verbatimno retriesno editingno cherry-pickingread-only http get — no javascript, no logins, no formsagent: deepseek-flashproducer: deepseek-v4-pro + live searchevery transcript published verbatim

Where it got interesting

done Yorkshire Wildlife Park: official statement and closure duckduckgo.com +10 more ⚠ 4 bot walls done USWNT v Spain: UK kickoff time and channel bbc.co.uk +10 more ⚠ 2 bot walls done Best readable source for Yorkshire tiger incident metro.co.uk +3 more ⚠ 1 bot wall

The other half: the 1215 most-visited sites, scored

Every week the 1215 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.

51/100average readiness score

13%publish llms.txt

27%block at least one AI crawler

19%closed to AI by policy

4%wouldn't answer at all

Who is ready, and who is not

25 sites answer every check perfectly, so the top of the ranking is a 25-way tie and tells you nothing. The spread, and the bottom, do.

118 grade A
239 grade B
189 grade C
119 grade D
321 grade F
229 closed by policy

Perfect 100/100 — 25 sites

Where agents get stuck — ranks 1211–1215 of 1215

#	Site	Grade
1211	naver.com closed by policy	Closed by policy
1212	quora.com closed by policy	Closed by policy
1213	realestate.com.au closed by policy	Closed by policy
1214	wordreference.com closed by policy	Closed by policy
1215	yelp.com closed by policy	Closed by policy

Full ranked index of 1215 sites →

Work on one of these sites? Every failed check on your report page has a concrete fix, and scores refresh weekly. Request an audit of any site — it's free and takes one issue.

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 (8 snapshots so far).