<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Agentic on Zachary Loeber's Blog</title><link>https://blog.zacharyloeber.com/tags/agentic/</link><description>Recent content in Agentic on Zachary Loeber's Blog</description><generator>Hugo</generator><language>en</language><lastBuildDate>Mon, 05 Jan 2026 09:21:07 -0600</lastBuildDate><atom:link href="https://blog.zacharyloeber.com/tags/agentic/index.xml" rel="self" type="application/rss+xml"/><item><title>LLM Underdogs of 2025</title><link>https://blog.zacharyloeber.com/article/llm-underdogs-of-2025/</link><pubDate>Mon, 05 Jan 2026 09:21:07 -0600</pubDate><guid>https://blog.zacharyloeber.com/article/llm-underdogs-of-2025/</guid><description>&lt;h1 id="llm-underdogs-of-2025">LLM Underdogs of 2025&lt;/h1>
&lt;p>2025 has been a flurry of AI madness that has been hard to keep up with. I&amp;rsquo;ve been deep in learning and experimenting in the AI space and noticed that while everyone&amp;rsquo;s hyping up the latest GPT variant or Claude release, there are some genuinely impressive open-source models that feel like they just flew under the radar in 2025. These aren&amp;rsquo;t just &amp;ldquo;good for their size&amp;rdquo;, they&amp;rsquo;re legit excellent models that you can run locally, for free, and deserve more attention.&lt;/p></description></item><item><title>Terraform Custom Module MCP Server</title><link>https://blog.zacharyloeber.com/article/terraform-custom-module-mcp-server/</link><pubDate>Wed, 22 Oct 2025 21:48:03 -0500</pubDate><guid>https://blog.zacharyloeber.com/article/terraform-custom-module-mcp-server/</guid><description>&lt;p>I created an MCP server that streamlines access to custom Terraform modules that I&amp;rsquo;d like to share with the community. The project called &lt;a href="https://github.com/zloeber/terraform-ingest">terraform-ingest&lt;/a> is a CLI, MCP, and API tool that can be used locally or with an AI agent to tap into your existing code base more effectively.&lt;/p></description></item><item><title>Create Terraform with AI and Github Copilot</title><link>https://blog.zacharyloeber.com/article/create-terraform-with-ai-and-github-copilot/</link><pubDate>Mon, 20 Oct 2025 11:43:11 -0500</pubDate><guid>https://blog.zacharyloeber.com/article/create-terraform-with-ai-and-github-copilot/</guid><description>&lt;p>Creating terraform or other infrastructure as code for a new project can be daunting for some. This shows how you can easily crank out a new deployment to meet your requirements using Github copilot prompt files and a few free MCP servers. For the heck of it, we will also convert between two totally different cloud providers to deploy the same infrastructure.&lt;/p></description></item><item><title>Cleaning Terraformer output with AI</title><link>https://blog.zacharyloeber.com/article/cagent-terraformer-rewrite/</link><pubDate>Fri, 19 Sep 2025 14:05:00 -0500</pubDate><guid>https://blog.zacharyloeber.com/article/cagent-terraformer-rewrite/</guid><description>&lt;p>This article will go over using a team of AI agents in conjunction with the &lt;a href="https://github.com/hashicorp/terraform-mcp-server">Terraform MCP server&lt;/a> and Docker&amp;rsquo;s &lt;a href="https://github.com/docker/cagent">cagent&lt;/a> tool to clean up some rather gnarly autogenerated terraform without needing to write any code.&lt;/p></description></item></channel></rss>