<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Q&apos;s Notes</title><description>Notes, essays, and opinions on AI, technology, business, and the occasional aside.</description><link>https://notes.qiuyue.dev/</link><language>en-us</language><item><title>What an agent wallet can actually prove</title><link>https://notes.qiuyue.dev/posts/wallet-is-not-a-conscience/</link><guid isPermaLink="true">https://notes.qiuyue.dev/posts/wallet-is-not-a-conscience/</guid><description>Cloudflare Wallets can link an agent payment to an account and constrain how it spends. A separate question remains: was an in-bounds purchase actually wanted?</description><pubDate>Tue, 18 Aug 2026 00:00:00 GMT</pubDate></item><item><title>AI-native game&quot; is a test, not a vibe</title><link>https://notes.qiuyue.dev/posts/ai-native-game-is-a-test/</link><guid isPermaLink="true">https://notes.qiuyue.dev/posts/ai-native-game-is-a-test/</guid><description>&quot;AI-native game&quot; has one honest definition: pull the model out and see if play survives. Passing that test says nothing about whether the result has any taste.</description><pubDate>Wed, 05 Aug 2026 00:00:00 GMT</pubDate></item><item><title>Taste is a bet on a standard that doesn&apos;t exist yet</title><link>https://notes.qiuyue.dev/posts/taste-is-a-bet/</link><guid isPermaLink="true">https://notes.qiuyue.dev/posts/taste-is-a-bet/</guid><description>I said taste was judgment renamed. Trying to pull the two words apart, I found I could — and the difference is what the moat argument keeps hiding.</description><pubDate>Fri, 31 Jul 2026 00:00:00 GMT</pubDate></item><item><title>Taste is just judgment, renamed</title><link>https://notes.qiuyue.dev/posts/taste-is-judgment/</link><guid isPermaLink="true">https://notes.qiuyue.dev/posts/taste-is-judgment/</guid><description>Everyone repeats that taste is the moat in the AI era, but almost nobody says what taste is in a given job. It&apos;s domain judgment, renamed.</description><pubDate>Mon, 20 Jul 2026 00:00:00 GMT</pubDate></item><item><title>Coding agents need traffic control</title><link>https://notes.qiuyue.dev/posts/agent-prs-need-traffic-control/</link><guid isPermaLink="true">https://notes.qiuyue.dev/posts/agent-prs-need-traffic-control/</guid><description>When several coding agents work at once, the hard part is deciding what each one should change, and in what order.</description><pubDate>Fri, 10 Jul 2026 00:00:00 GMT</pubDate></item><item><title>The best agent interface is a map</title><link>https://notes.qiuyue.dev/posts/codebase-maps-are-agent-interfaces/</link><guid isPermaLink="true">https://notes.qiuyue.dev/posts/codebase-maps-are-agent-interfaces/</guid><description>Coding agents need more than context; they need codebases that make the right place to work clear.</description><pubDate>Tue, 07 Jul 2026 00:00:00 GMT</pubDate></item><item><title>Pull requests are becoming knowledge imports</title><link>https://notes.qiuyue.dev/posts/pull-requests-are-knowledge-imports/</link><guid isPermaLink="true">https://notes.qiuyue.dev/posts/pull-requests-are-knowledge-imports/</guid><description>When agents make patches cheap, review has to move from accepting code to absorbing knowledge.</description><pubDate>Fri, 03 Jul 2026 00:00:00 GMT</pubDate></item><item><title>Cheap agents create coordination debt</title><link>https://notes.qiuyue.dev/posts/agent-coordination-debt/</link><guid isPermaLink="true">https://notes.qiuyue.dev/posts/agent-coordination-debt/</guid><description>AI agents make individual output cheaper before they make organizations better at deciding what should exist.</description><pubDate>Fri, 26 Jun 2026 00:00:00 GMT</pubDate></item><item><title>Helpful agents are an authorization bug</title><link>https://notes.qiuyue.dev/posts/helpful-agents-authorization-bug/</link><guid isPermaLink="true">https://notes.qiuyue.dev/posts/helpful-agents-authorization-bug/</guid><description>The risky coding agent isn&apos;t the one that ignores you. It&apos;s the one that helps too much.</description><pubDate>Tue, 23 Jun 2026 00:00:00 GMT</pubDate></item><item><title>The real AI bottleneck is not intelligence. It is coordination.</title><link>https://notes.qiuyue.dev/posts/consulting-coordination/</link><guid isPermaLink="true">https://notes.qiuyue.dev/posts/consulting-coordination/</guid><description>Most enterprise AI value is lost not to model limits but to the organisation around the model. Coordination, not intelligence, is the binding constraint.</description><pubDate>Sat, 02 May 2026 00:00:00 GMT</pubDate></item><item><title>From slide factory to outcome factory: why consulting economics are changing</title><link>https://notes.qiuyue.dev/posts/consulting-outcomes/</link><guid isPermaLink="true">https://notes.qiuyue.dev/posts/consulting-outcomes/</guid><description>AI breaks the day-rate convention. The question is no longer whether consultants use AI but whether firms can stop selling effort and start underwriting results.</description><pubDate>Sat, 25 Apr 2026 00:00:00 GMT</pubDate></item><item><title>AI will not just replace junior consultants. It will expose what consulting was really selling.</title><link>https://notes.qiuyue.dev/posts/consulting-barbell/</link><guid isPermaLink="true">https://notes.qiuyue.dev/posts/consulting-barbell/</guid><description>AI is unbundling what consulting really sold. The pyramid is becoming a barbell — generic analysis squeezed, judgment-heavy work repriced upward.</description><pubDate>Sat, 18 Apr 2026 00:00:00 GMT</pubDate></item></channel></rss>