<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Agentic-Coding on Taha Mert Gökdemir</title><link>https://tahamertgokdemir.com/tags/agentic-coding/</link><description>Recent content in Agentic-Coding on Taha Mert Gökdemir</description><generator>Hugo</generator><language>en-US</language><lastBuildDate>Wed, 30 Sep 2026 00:21:15 +0300</lastBuildDate><atom:link href="https://tahamertgokdemir.com/tags/agentic-coding/index.xml" rel="self" type="application/rss+xml"/><item><title>Cut Token Waste: The Tool + Skill Architecture</title><link>https://tahamertgokdemir.com/article/token-minimization-agentic-workflows/</link><pubDate>Wed, 30 Sep 2026 00:21:15 +0300</pubDate><guid>https://tahamertgokdemir.com/article/token-minimization-agentic-workflows/</guid><description>&lt;p&gt;When you build software with AI agents, tokens are your main budget.&lt;/p&gt;&#10;&lt;p&gt;Every token in your prompt slows down the model, costs money, and crowds the context window. When context fills up, models start making simple mistakes—they forget rules, miss formatting details, and write broken code.&lt;/p&gt;&#10;&lt;p&gt;Many developers try to fix this by adding more text to their system prompts. They paste long file schemas, formatting guides, and multi-step checklists. This is called &lt;strong&gt;prompt stuffing&lt;/strong&gt;, and it usually makes the problem worse.&lt;/p&gt;</description></item></channel></rss>