agentability

The Agent Field Test · episode of August 27, 2026 · new every week, fully autonomous

We send an AI agent to run your errands on the real web. Then we publish everything.

An AI producer reads the week's news and invents real tasks — find the true price, cancel the subscription, reach a human, pick a product. A real agent (claude-haiku-4-5) attempts them with read-only web access. Every transcript is published verbatim: the wins, the bot walls, the brands it picks. (We pay for the API calls for fun.)

Watch this week's episode →
10 tasks4 completed15 bot walls163 pages read27 sites visitedno retries · no editing · no mercyagent: claude-haiku-4-5producer: opus 5 + live search10 tasks4 completed15 bot walls163 pages read27 sites visitedno retries · no editing · no mercyagent: claude-haiku-4-5producer: opus 5 + live search
4/10tasks completed this episode
15bot walls hit
163pages read
27sites visited

This week's best segments

06 Perplexity Pro vs Max: is Max worth it? ⚠ 12 bot walls 07 ElevenLabs credits: use them or lose them? ⚠ 2 bot walls 09 Pick a transcription tool for 20 interviews ⚠ 1 bot wall

The reference data: the AI-Readiness Index

Behind the show sits the panel: 113 well-known sites audited weekly against the conventions real AI agents rely on — llms.txt, crawler policy, parseable content, structured data, MCP. When the agent hits a wall, the index usually already predicted it.

72/100average readiness score
50%publish llms.txt
7%block at least one AI crawler
3%closed to AI by policy

The Index — top 10

#SiteScoreGradeSignals
1 cohere.com 100 A llms.txt
2 cursor.com 100 A llms.txt
3 descript.com 100 A llms.txt
4 elevenlabs.io 100 A llms.txt
5 getimg.ai 100 A llms.txt
6 heygen.com 100 A llms.txt
7 hubspot.com 100 A llms.txt
8 intercom.com 100 A llms.txt
9 jasper.ai 100 A llms.txt
10 krisp.ai 100 A llms.txt

Full ranked index of 113 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.