<?xml version="1.0" encoding="utf-8" standalone="yes" ?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>TypeScript on Fabian G. Williams</title>
    <link>https://www.fabswill.com/tags/typescript/</link>
    <description>Recent content in TypeScript on Fabian G. Williams</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>en</language>
    <lastBuildDate>Sun, 10 Aug 2025 00:00:00 +0000</lastBuildDate>
    
	<atom:link href="https://www.fabswill.com/tags/typescript/index.xml" rel="self" type="application/rss+xml" />
    
    
    <item>
      <title>Agent &#43; Local Model &#43; Evals — One‑Pager</title>
      <link>https://www.fabswill.com/blog/2025-08-10-agent-plus-local-model-plus-evals-onepager/</link>
      <pubDate>Sun, 10 Aug 2025 00:00:00 +0000</pubDate>
      
      <guid>https://www.fabswill.com/blog/2025-08-10-agent-plus-local-model-plus-evals-onepager/</guid>
      <description>🚀 Purpose If you’ve ever wondered how to compare a locally‑hosted LLM with a hosted OpenAI model side‑by‑side, while keeping the whole experiment observable from end‑to‑end, you’re in the right place. This one‑pager walks you through the starter repo that stitches together three distinct paths:
   Path Stack Observability     A .NET 8 + Semantic Kernel + Ollama (local model) Azure Monitor (OTEL)   B OpenAI Agents SDK (TypeScript/Node) OpenAI Logs → optional OTLP → Azure Monitor   C Python Evals (OpenAI‑provided) Same prompts, same metrics    The goal?</description>
    </item>
    
  </channel>
</rss>