<?xml version="1.0" encoding="UTF-8"?>
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:video="http://www.google.com/schemas/sitemap-video/1.1">
<url>
<loc>https://codestoa.com/</loc>
<lastmod>2026-10-25</lastmod>
<changefreq>daily</changefreq>
<priority>1</priority>
</url>
<url>
<loc>https://codestoa.com/ai-engineering/</loc>
<lastmod>2026-10-25</lastmod>
<changefreq>weekly</changefreq>
<priority>0.8</priority>
</url>
<url>
<loc>https://codestoa.com/system-design/</loc>
<lastmod>2026-10-23</lastmod>
<changefreq>weekly</changefreq>
<priority>0.8</priority>
</url>
<url>
<loc>https://codestoa.com/ai-engineering/agent-guardrails/</loc>
<video:video>
<video:title>AI Agent Guardrails: Limits That Keep an Agent Safe</video:title>
<video:thumbnail_loc>https://media.codestoa.com/ai-engineering/agent-guardrails/poster.jpg?v=1c74bb60</video:thumbnail_loc>
<video:description>What AI agent guardrails are, where they sit in the agent loop, and six kinds with examples: input checks, tool permissions, limits, approval and budgets.</video:description>
<video:content_loc>https://media.codestoa.com/ai-engineering/agent-guardrails/long.mp4?v=95e03587</video:content_loc>
</video:video>
<lastmod>2026-10-25</lastmod>
<changefreq>monthly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://codestoa.com/ai-engineering/agent-loop/</loc>
<video:video>
<video:title>The Agent Loop: How an LLM Plans, Acts and Knows When to Stop</video:title>
<video:thumbnail_loc>https://media.codestoa.com/ai-engineering/agent-loop/poster.jpg?v=e97f79c1</video:thumbnail_loc>
<video:description>How an agent loop works: the model picks a tool, your code runs it, the result goes back into the history, and guards decide when the loop must stop.</video:description>
<video:content_loc>https://media.codestoa.com/ai-engineering/agent-loop/long.mp4?v=f58bc1b4</video:content_loc>
</video:video>
<lastmod>2026-10-24</lastmod>
<changefreq>monthly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://codestoa.com/ai-engineering/agent-tool-calling/</loc>
<video:video>
<video:title>Tool Calling: How an Agent Picks and Uses a Tool</video:title>
<video:thumbnail_loc>https://media.codestoa.com/ai-engineering/agent-tool-calling/poster.jpg?v=7675fdb0</video:thumbnail_loc>
<video:description>Tool calling (function calling) explained: the model never runs the tool, it only writes the call. How it picks a tool, fills arguments, and when to call none.</video:description>
<video:content_loc>https://media.codestoa.com/ai-engineering/agent-tool-calling/long.mp4?v=d42e03fb</video:content_loc>
</video:video>
<lastmod>2026-10-24</lastmod>
<changefreq>monthly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://codestoa.com/ai-engineering/jev-decision-model/</loc>
<video:video>
<video:title>Jev Explained: A Decision Model vs an LLM</video:title>
<video:thumbnail_loc>https://media.codestoa.com/ai-engineering/jev-decision-model/poster.jpg?v=cd7942c0</video:thumbnail_loc>
<video:description>What a decision model like Jev is, how it differs from an LLM, what's confirmed vs vendor-claimed, and when picking from a list with a score beats text.</video:description>
<video:content_loc>https://media.codestoa.com/ai-engineering/jev-decision-model/long.mp4?v=ceb871b7</video:content_loc>
</video:video>
<lastmod>2026-10-24</lastmod>
<changefreq>monthly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://codestoa.com/ai-engineering/llm-eval-methods/</loc>
<video:video>
<video:title>LLM Eval Methods: Code Checks, Human Review and LLM-as-Judge</video:title>
<video:thumbnail_loc>https://media.codestoa.com/ai-engineering/llm-eval-methods/poster.jpg?v=44921fc5</video:thumbnail_loc>
<video:description>Learn the three LLM eval methods (code checks, LLM-as-judge and human review), when to use each, their limits and how real eval suites layer them.</video:description>
<video:content_loc>https://media.codestoa.com/ai-engineering/llm-eval-methods/long.mp4?v=cf062a9f</video:content_loc>
</video:video>
<lastmod>2026-10-23</lastmod>
<changefreq>monthly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://codestoa.com/ai-engineering/llm-evals-introduction/</loc>
<video:video>
<video:title>LLM Evals: Why "It Looks Good" Isn't Enough</video:title>
<video:thumbnail_loc>https://media.codestoa.com/ai-engineering/llm-evals-introduction/poster.jpg?v=14bf10b6</video:thumbnail_loc>
<video:description>What LLM evals are, why a few manual prompts aren't testing, and the seven-step workflow engineers use to measure AI apps before users find the failures.</video:description>
<video:content_loc>https://media.codestoa.com/ai-engineering/llm-evals-introduction/long.mp4?v=024d9c4f</video:content_loc>
</video:video>
<lastmod>2026-10-19</lastmod>
<changefreq>monthly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://codestoa.com/ai-engineering/llm-evaluation-criteria/</loc>
<video:video>
<video:title>LLM Evaluation Criteria: Quality, Safety and Operational Metrics</video:title>
<video:thumbnail_loc>https://media.codestoa.com/ai-engineering/llm-evaluation-criteria/poster.jpg?v=98d2ab89</video:thumbnail_loc>
<video:description>Learn which LLM evaluation criteria to measure: answer quality, safety and operational metrics, told through one support bot, plus a runnable report card.</video:description>
<video:content_loc>https://media.codestoa.com/ai-engineering/llm-evaluation-criteria/long.mp4?v=0b22fdff</video:content_loc>
</video:video>
<lastmod>2026-10-22</lastmod>
<changefreq>monthly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://codestoa.com/ai-engineering/llm-failure-points/</loc>
<video:video>
<video:title>Failure Points in LLM Applications: Where RAG Apps Break</video:title>
<video:thumbnail_loc>https://media.codestoa.com/ai-engineering/llm-failure-points/poster.jpg?v=780f7b47</video:thumbnail_loc>
<video:description>Follow one question through a RAG chatbot to see where LLM apps fail: retriever, generator, workflow and application, and why one eval pipeline isn't enough.</video:description>
<video:content_loc>https://media.codestoa.com/ai-engineering/llm-failure-points/long.mp4?v=04d99da6</video:content_loc>
</video:video>
<lastmod>2026-10-22</lastmod>
<changefreq>monthly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://codestoa.com/system-design/back-of-the-envelope-estimation/</loc>
<video:video>
<video:title>Back-of-the-Envelope Estimation for System Design</video:title>
<video:thumbnail_loc>https://media.codestoa.com/system-design/back-of-the-envelope-estimation/poster.jpg?v=4250c6c1</video:thumbnail_loc>
<video:description>Learn back-of-the-envelope estimation: work out requests per second, peak load, storage and bandwidth with round numbers, and let them decide your design.</video:description>
<video:content_loc>https://media.codestoa.com/system-design/back-of-the-envelope-estimation/long.mp4?v=a3cb3b26</video:content_loc>
</video:video>
<lastmod>2026-10-23</lastmod>
<changefreq>monthly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://codestoa.com/system-design/how-to-approach-system-design/</loc>
<video:video>
<video:title>How to Approach a System Design Problem, Step by Step</video:title>
<video:thumbnail_loc>https://media.codestoa.com/system-design/how-to-approach-system-design/poster.jpg?v=a9cfd007</video:thumbnail_loc>
<video:description>A five-step way to approach any system design problem or interview: clarify requirements, estimate, sketch the design, deep dive, then trade-offs.</video:description>
<video:content_loc>https://media.codestoa.com/system-design/how-to-approach-system-design/long.mp4?v=3192d77e</video:content_loc>
</video:video>
<lastmod>2026-10-23</lastmod>
<changefreq>monthly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://codestoa.com/system-design/what-is-system-design/</loc>
<video:video>
<video:title>What Is System Design? The Parts, the Promises and the Trade-offs</video:title>
<video:thumbnail_loc>https://media.codestoa.com/system-design/what-is-system-design/poster.jpg?v=c5031dd7</video:thumbnail_loc>
<video:description>What system design is, in plain words: the parts of a system, how they connect, the promises it keeps under load, and why every design is a trade-off.</video:description>
<video:content_loc>https://media.codestoa.com/system-design/what-is-system-design/long.mp4?v=221aa10d</video:content_loc>
</video:video>
<lastmod>2026-10-23</lastmod>
<changefreq>monthly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://codestoa.com/about/</loc>
<changefreq>yearly</changefreq>
<priority>0.3</priority>
</url>
<url>
<loc>https://codestoa.com/privacy/</loc>
<changefreq>yearly</changefreq>
<priority>0.1</priority>
</url>
</urlset>
