<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0">
  <channel>
    <title>Aziz Khan · Writing</title>
    <link>https://justaziz.com/writing</link>
    <description>Notes on building AI products, agents and production systems.</description>
    <language>en</language>
    <item>
      <title>How to Take an AI-Built App from Prototype to Production</title>
      <link>https://justaziz.com/writing/prototype-to-production-ai-built-app</link>
      <guid>https://justaziz.com/writing/prototype-to-production-ai-built-app</guid>
      <pubDate>Tue, 17 Nov 2026 00:00:00 GMT</pubDate>
      <description>A working checklist for apps built with AI coding tools: secrets, data access, config, payments, background work, deploys and monitoring.</description>
    </item>
    <item>
      <title>Why AI Agents Fail in Production and How to Fix Them</title>
      <link>https://justaziz.com/writing/why-ai-agents-fail-in-production</link>
      <guid>https://justaziz.com/writing/why-ai-agents-fail-in-production</guid>
      <pubDate>Tue, 17 Nov 2026 00:00:00 GMT</pubDate>
      <description>Eight ways AI agents break once real users and real data arrive, how to recognize each one, and the fix that holds.</description>
    </item>
    <item>
      <title>Why I built Zippy: tickets in, verified work out</title>
      <link>https://justaziz.com/writing/why-i-built-zippy</link>
      <guid>https://justaziz.com/writing/why-i-built-zippy</guid>
      <pubDate>Sat, 31 Oct 2026 00:00:00 GMT</pubDate>
      <description>Running Claude Code agents on real tickets, each in its own git worktree, and why the review step matters more than the agent.</description>
    </item>
    <item>
      <title>My AI-native dev loop: agents build, I decide</title>
      <link>https://justaziz.com/writing/ai-native-dev-loop</link>
      <guid>https://justaziz.com/writing/ai-native-dev-loop</guid>
      <pubDate>Sat, 24 Oct 2026 00:00:00 GMT</pubDate>
      <description>How I split work between coding agents and myself so speed goes up without quality going down.</description>
    </item>
    <item>
      <title>How Uxlyze audits a landing page with headless Chrome and Gemini</title>
      <link>https://justaziz.com/writing/how-uxlyze-audits-a-landing-page</link>
      <guid>https://justaziz.com/writing/how-uxlyze-audits-a-landing-page</guid>
      <pubDate>Sat, 17 Oct 2026 00:00:00 GMT</pubDate>
      <description>The architecture behind an AI UX audit tool: a Go worker, chromedp, a job queue and structured LLM output.</description>
    </item>
    <item>
      <title>Two rules you can't fix later in a multi-tenant SaaS</title>
      <link>https://justaziz.com/writing/multi-tenant-rules-you-cant-fix-later</link>
      <guid>https://justaziz.com/writing/multi-tenant-rules-you-cant-fix-later</guid>
      <pubDate>Sat, 10 Oct 2026 00:00:00 GMT</pubDate>
      <description>Enforce tenancy in Postgres, not the app, and never let money touch a float. Lessons from building Traveo.</description>
    </item>
    <item>
      <title>Designing sending limits for a WhatsApp messaging API</title>
      <link>https://justaziz.com/writing/messaging-api-sending-limits</link>
      <guid>https://justaziz.com/writing/messaging-api-sending-limits</guid>
      <pubDate>Sat, 03 Oct 2026 00:00:00 GMT</pubDate>
      <description>Warm-up curves, quiet hours, new-contact caps and why a held message should queue, not drop. Notes from building FoxlyFlow.</description>
    </item>
    <item>
      <title>Build the SaaS before you have the API keys</title>
      <link>https://justaziz.com/writing/adapters-with-mock-defaults</link>
      <guid>https://justaziz.com/writing/adapters-with-mock-defaults</guid>
      <pubDate>Sat, 26 Sep 2026 00:00:00 GMT</pubDate>
      <description>How Pavly runs every third-party integration behind adapters that default to mocks, and why keyword rules run before the AI.</description>
    </item>
  </channel>
</rss>