<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Visual Studio Code on Coderrob</title><link>https://coderrob.com/tags/visual-studio-code/</link><description>Recent content in Visual Studio Code on Coderrob</description><generator>Hugo</generator><language>en-US</language><lastBuildDate>Fri, 24 Oct 2025 09:00:00 -0500</lastBuildDate><atom:link href="https://coderrob.com/tags/visual-studio-code/index.xml" rel="self" type="application/rss+xml"/><item><title>Reverse Engineering Agentic Workflows from Copilot Debug Logs</title><link>https://coderrob.com/posts/reverse-engineering-agentic-workflows-from-copilot-debug-logs/</link><pubDate>Fri, 24 Oct 2025 09:00:00 -0500</pubDate><guid>https://coderrob.com/posts/reverse-engineering-agentic-workflows-from-copilot-debug-logs/</guid><description>&lt;p&gt;Here&amp;rsquo;s a secret weapon for building your own agentic workflows: &lt;strong&gt;GitHub Copilot Chat&amp;rsquo;s debug logs&lt;/strong&gt;.&lt;/p&gt;
&lt;p&gt;You know how everyone&amp;rsquo;s out there wrestling with hallucinating AI agents? Trying to figure out how to structure those prompts, which tools to call when, how to handle errors without pulling your hair out, what context to pass between steps&amp;hellip;&lt;/p&gt;
&lt;p&gt;The answer?&lt;/p&gt;
&lt;p&gt;It&amp;rsquo;s sitting right there in your Copilot Chat debug view. Already solved. Already tested. Already proven to work for &lt;em&gt;your&lt;/em&gt; specific use cases.&lt;/p&gt;</description></item><item><title>Local LLMs as a Code Assistant in Visual Studio Code</title><link>https://coderrob.com/posts/local-llms-as-a-code-assistant-in-visual-studio-code/</link><pubDate>Tue, 03 Dec 2024 10:00:17 -0600</pubDate><guid>https://coderrob.com/posts/local-llms-as-a-code-assistant-in-visual-studio-code/</guid><description>&lt;p&gt;I have been using a Visual Studio Code extension called &lt;a href="https://marketplace.visualstudio.com/items?itemName=Continue.continue"&gt;Continue&lt;/a&gt;, and it has become one of my favorite ways to work with local LLMs.&lt;/p&gt;
&lt;p&gt;The short version:&lt;/p&gt;
&lt;blockquote&gt;
&lt;p&gt;Continue lets you bring AI-assisted coding into VS Code while keeping the model, prompts, and workflow under your control.&lt;/p&gt;
&lt;/blockquote&gt;
&lt;p&gt;That matters more than it sounds like it does.&lt;/p&gt;
&lt;h2 id="why-local-matters"&gt;Why Local Matters&lt;/h2&gt;
&lt;p&gt;Local models are not always the strongest models.&lt;/p&gt;
&lt;p&gt;They are not always the fastest models.&lt;/p&gt;</description></item></channel></rss>