<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Developer-Tools on jeeVee Blog</title>
    <link>https://blog.jeevee.dev/blog/developer-tools/</link>
    <description>Recent content in Developer-Tools on jeeVee Blog</description>
    <generator>Hugo</generator>
    <language>en-US</language>
    <copyright>Copyright © 2025, GV.</copyright>
    <lastBuildDate>Sat, 10 May 2025 13:12:45 +0000</lastBuildDate>
    <atom:link href="https://blog.jeevee.dev/blog/developer-tools/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Observability</title>
      <link>https://blog.jeevee.dev/agentic/observability/</link>
      <pubDate>Sat, 10 May 2025 13:12:45 +0000</pubDate>
      <guid>https://blog.jeevee.dev/agentic/observability/</guid>
      <description>&lt;h2 id=&#34;observability&#34;&gt;Observability&lt;/h2&gt;&#xA;&lt;p&gt;I have not seen this feature highlighted in other agentic systems, but my own experience building my system was that it is paramount to be able to see what the LLM conversation was, and even more, to be able to make amendments to the conversations.&lt;/p&gt;&#xA;&lt;h3 id=&#34;reviewing-the-detailed-llm-log&#34;&gt;Reviewing the detailed LLM log&lt;/h3&gt;&#xA;&lt;p&gt;This is incredibly valuable, as many problems can be traced to prompt and context engineering. The log shows what was actually sent to the LLM and I can review if I missed anything salient to the task I asked to be solved. The logs live locally in a WASM SQLite database in the browser.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
