See which everyday web errands an AI agent can actually finish
Agentability is a weekly public experiment where a real AI agent attempts ten everyday web errands and every transcript is published verbatim.
Source
khalidsaidi on Hacker News · 2026-10-06 · Project link
Written in our own words. Credit to the original author. Link checked 2026-10-23.
What they did
Agentability is a weekly public experiment where a real AI agent attempts ten everyday web errands and every transcript is published verbatim.
Result (as claimed)
In the week shown it finished 7 of 10 errands and hit 20 bot walls; 1,219 popular sites are also scored.
Tools they used
Cost: Pricing depends on the tools you pick; check each official pricing page.
Set it up
Gather your sources
Collect the papers, notes, links or files you want to work from in one place.
Load them into the tool
Open Agentability and add your sources. Keep the original files so you can check claims later.
Ask focused questions
Ask for summaries, comparisons or connections with citations to the source passages.
Verify and save
Spot check claims against the sources, then save the output as notes you can reuse.
Copy the full setup prompt
Paste into your agent and it will walk you through the setup, asking before anything that sends, posts or spends.
You are helping me set up this AI use case end to end in Claude Code. Goal: See which everyday web errands an AI agent can actually finish What the original author did: Agentability is a weekly public experiment where a real AI agent attempts ten everyday web errands and every transcript is published verbatim. Reported result (as claimed by the author): In the week shown it finished 7 of 10 errands and hit 20 bot walls; 1,219 popular sites are also scored. Source: https://news.ycombinator.com/item?id=49984736 Tools they used: Agentability Category: Research & learning Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
You are helping me set up this AI use case end to end in Codex. Goal: See which everyday web errands an AI agent can actually finish What the original author did: Agentability is a weekly public experiment where a real AI agent attempts ten everyday web errands and every transcript is published verbatim. Reported result (as claimed by the author): In the week shown it finished 7 of 10 errands and hit 20 bot walls; 1,219 popular sites are also scored. Source: https://news.ycombinator.com/item?id=49984736 Tools they used: Agentability Category: Research & learning Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
You are helping me set up this AI use case end to end in Grok Bot. Goal: See which everyday web errands an AI agent can actually finish What the original author did: Agentability is a weekly public experiment where a real AI agent attempts ten everyday web errands and every transcript is published verbatim. Reported result (as claimed by the author): In the week shown it finished 7 of 10 errands and hit 20 bot walls; 1,219 popular sites are also scored. Source: https://news.ycombinator.com/item?id=49984736 Tools they used: Agentability Category: Research & learning Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
The Daily 5
Get five new use cases tomorrow morning
Free. Real sources. Unsubscribe any time.
Guides for this use case
Related use cases
Turn your kid's vocab app into a web app when App Store review stalls
A parent made an app to help his daughter learn German vocabulary. Stuck in a third round of App Store review over his walkthrough video, he asked Claude to turn it into a PWA instead.
Turn PDFs, scans and web pages into AI-ready Markdown on your own machine
Sygal converts PDF, Word, Excel, images, web pages and even YouTube links into clean Markdown and JSON locally, so documents drop into a prompt or knowledge base with far fewer tokens.
Test which services coding agents pick when you don't name one
A researcher asked Claude Code and Codex to build things without specifying providers and logged which databases, hosts and APIs they chose.
Crawl the web for agents without an LLM in the crawl loop
Built Jevcrawl, an MCP and CLI crawler that finds answer pages more often without calling an LLM while crawling.