<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Essays — Kafilat Emmanuel</title><description>Long-form essays on building systems, strategy, and AI.</description><link>https://kafilatemmanuel.com/</link><language>en-us</language><item><title>When Building Got Cheap</title><link>https://kafilatemmanuel.com/essays/when-building-got-cheap/</link><guid isPermaLink="true">https://kafilatemmanuel.com/essays/when-building-got-cheap/</guid><description>Two years ago, automating a single ETL flow took me weeks. This week I built a full internal tool in five days. The real shift isn&apos;t better AI tools — it&apos;s the collapse of the cost of problem-solving, and what that does to the SaaS math.</description><pubDate>Wed, 21 Jan 2026 00:00:00 GMT</pubDate></item><item><title>Copilot Isn&apos;t a Strategy</title><link>https://kafilatemmanuel.com/essays/copilot-isnt-a-strategy/</link><guid isPermaLink="true">https://kafilatemmanuel.com/essays/copilot-isnt-a-strategy/</guid><description>Buying a generalist chatbot raises the floor of competence. It doesn&apos;t build your edge. True value comes from bespoke systems that understand your specific business logic and data.</description><pubDate>Wed, 07 Jan 2026 00:00:00 GMT</pubDate></item><item><title>Browsers Have a Ceiling</title><link>https://kafilatemmanuel.com/essays/browsers-have-a-ceiling/</link><guid isPermaLink="true">https://kafilatemmanuel.com/essays/browsers-have-a-ceiling/</guid><description>A week in Google Meet taught me something about architecture constraints. You can&apos;t brute-force performance through a browser tab.</description><pubDate>Tue, 30 Dec 2025 00:00:00 GMT</pubDate></item><item><title>Three Rules I Earned the Expensive Way</title><link>https://kafilatemmanuel.com/essays/three-rules-earned-the-expensive-way/</link><guid isPermaLink="true">https://kafilatemmanuel.com/essays/three-rules-earned-the-expensive-way/</guid><description>After nearly a thousand hours building with Claude Code, I&apos;ve learned a few lessons the expensive way. These are my three non-negotiable rules for every AI coding agent.</description><pubDate>Thu, 11 Dec 2025 00:00:00 GMT</pubDate></item><item><title>The Work Slop Problem Isn&apos;t AI — It&apos;s Misuse of AI Modes</title><link>https://kafilatemmanuel.com/essays/cognitive-and-operational-mode/</link><guid isPermaLink="true">https://kafilatemmanuel.com/essays/cognitive-and-operational-mode/</guid><description>AI has two modes: Cognitive and Operational. Work slop comes from treating everything like Cognitive Mode. The fix is knowing when to constrain AI to data-backed execution.</description><pubDate>Wed, 26 Nov 2025 00:00:00 GMT</pubDate></item><item><title>Document Everything</title><link>https://kafilatemmanuel.com/essays/document-everything/</link><guid isPermaLink="true">https://kafilatemmanuel.com/essays/document-everything/</guid><description>I manage countless scripts, four production apps, one in development, and another in planning. The hardest part isn&apos;t building them. It&apos;s making sure they&apos;re still understandable six months from now.</description><pubDate>Wed, 05 Nov 2025 00:00:00 GMT</pubDate></item><item><title>The Two-Front War</title><link>https://kafilatemmanuel.com/essays/the-two-front-war/</link><guid isPermaLink="true">https://kafilatemmanuel.com/essays/the-two-front-war/</guid><description>For weeks, the dream of bridging our underwriting models to the data warehouse felt like a fantasy. The breakthrough came when I stopped patching cracks and rebuilt the foundation.</description><pubDate>Tue, 14 Oct 2025 00:00:00 GMT</pubDate></item><item><title>Deciding What&apos;s First</title><link>https://kafilatemmanuel.com/essays/deciding-whats-first/</link><guid isPermaLink="true">https://kafilatemmanuel.com/essays/deciding-whats-first/</guid><description>The hardest part of building in the age of AI isn&apos;t figuring out what&apos;s possible. It&apos;s deciding what gets built first when the barriers to solutions have collapsed.</description><pubDate>Mon, 29 Sep 2025 00:00:00 GMT</pubDate></item><item><title>Before the Second Brain, I Had to Tame the Inbox</title><link>https://kafilatemmanuel.com/essays/before-the-second-brain-the-inbox/</link><guid isPermaLink="true">https://kafilatemmanuel.com/essays/before-the-second-brain-the-inbox/</guid><description>The first version of our document routing agent hit 37.5% accuracy. The problem wasn&apos;t the AI — it was building probabilistic inference into a step that needed to be deterministic.</description><pubDate>Mon, 22 Sep 2025 00:00:00 GMT</pubDate></item></channel></rss>