<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>DataKnife Lab Notes</title><description>Development logs, research explanations, experiments, and observations from a research-driven AI product studio.</description><link>https://dataknife.io/</link><language>en-us</language><item><title>Why a client studio builds its own products</title><link>https://dataknife.io/notes/why-we-build-our-own-products/</link><guid isPermaLink="true">https://dataknife.io/notes/why-we-build-our-own-products/</guid><description>Our internal products are not side projects — they are how we test our research honestly before we ask a client to bet on it.</description><pubDate>Thu, 02 Jul 2026 00:00:00 GMT</pubDate></item><item><title>Notifications are the wrong abstraction for agent work</title><link>https://dataknife.io/notes/notifications-are-the-wrong-abstraction/</link><guid isPermaLink="true">https://dataknife.io/notes/notifications-are-the-wrong-abstraction/</guid><description>Why the notification — the atomic unit of every alerting system — fails as an interface primitive once AI agents work for hours at a time, and what we&apos;re building instead.</description><pubDate>Wed, 24 Jun 2026 00:00:00 GMT</pubDate></item></channel></rss>