<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0"><channel><title>Omer Bin Saleem · Build with AI</title><link>https://www.omerbinsaleem.com</link><description>Daily AI hacks for builders: what each new AI feature lets you make, with the steps and the prompt to copy.</description>
<item><title>A 94 second launch film from one HTML file</title><link>https://www.omerbinsaleem.com/hacks/launch-film-from-one-html-file/</link><guid>https://www.omerbinsaleem.com/hacks/launch-film-from-one-html-file/</guid><pubDate>Thu, 22 Oct 2026 06:00:00 GMT</pubDate><description>No editor was opened. One HTML file of 436 lines, 14 script lines read by a local voice model, every cut snapped to a 112 BPM beat grid, 11 phone recordings inside a CSS phone, 2,838 frames rendered in 62 seconds.</description></item>
<item><title>3 print CSS traps that broke my PDFs</title><link>https://www.omerbinsaleem.com/hacks/print-css-traps/</link><guid>https://www.omerbinsaleem.com/hacks/print-css-traps/</guid><pubDate>Wed, 21 Oct 2026 06:00:00 GMT</pubDate><description>Our PDF preview took 11 seconds and still did not match the screen. Printing the same HTML the editor renders, with headless Chromium, took it to 2.5 s cold and a 30 ms render. Three print-CSS traps cost a round each.</description></item>
<item><title>The feature walkthrough that floated into empty space</title><link>https://www.omerbinsaleem.com/hacks/feature-guide-floating-bubble/</link><guid>https://www.omerbinsaleem.com/hacks/feature-guide-floating-bubble/</guid><pubDate>Tue, 20 Oct 2026 06:00:00 GMT</pubDate><description>An in-app guide fired on mount, tried to anchor to an element inside a conditional section, found nothing, and drifted. The fix is one check per step: is the target in the DOM right now? If not, skip it.</description></item>
<item><title>Put a 0.25 second judge in front of your AI agents</title><link>https://www.omerbinsaleem.com/hacks/small-judge-model/</link><guid>https://www.omerbinsaleem.com/hacks/small-judge-model/</guid><pubDate>Mon, 19 Oct 2026 06:00:00 GMT</pubDate><description>Big models do the work. Around that work sit hundreds of small yes-or-no questions a day. A small judge model answered 116,097 of them in 20 days, in a median of 245 ms, and only acts alone above a confidence gate.</description></item>
<item><title>My AI tester took 9 minutes and proved nothing. A week later: 1 minute, one real bug.</title><link>https://www.omerbinsaleem.com/hacks/teach-the-agent-first/</link><guid>https://www.omerbinsaleem.com/hacks/teach-the-agent-first/</guid><pubDate>Sun, 18 Oct 2026 06:00:00 GMT</pubDate><description>When an agent disappoints, most people swap the model. The fix was what it knows before it starts: a steps file instead of a script, a playbook, and a lessons file it writes itself.</description></item>
<item><title>Lead a team of AI agents, not one chatbot</title><link>https://www.omerbinsaleem.com/hacks/lead-a-team-of-ai-agents/</link><guid>https://www.omerbinsaleem.com/hacks/lead-a-team-of-ai-agents/</guid><pubDate>Sat, 17 Oct 2026 06:00:00 GMT</pubDate><description>One lead you talk to, narrow agents that each do one job, and a gate in front of anything you cannot undo. This week the team got its own lanes, a QA runner, a rule book and a voice.</description></item>
<item><title>Your team's questions already have answers. Give them a command.</title><link>https://www.omerbinsaleem.com/hacks/jarvis-commands/</link><guid>https://www.omerbinsaleem.com/hacks/jarvis-commands/</guid><pubDate>Thu, 15 Oct 2026 06:00:00 GMT</pubDate><description>Every week the same four questions hit the team channel. The answers were already in Jenkins, GitLab, the gateway and Jira. Four read-only commands now answer them in seconds.</description></item>
</channel></rss>
