<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Prompting on Programmer.ie: Modern AI programming</title>
    <link>http://programmer.ie/tags/prompting/</link>
    <description>Recent content in Prompting on Programmer.ie: Modern AI programming</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <atom:link href="http://programmer.ie/tags/prompting/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Designing Your First Agent (On Your Phone)</title>
      <link>http://programmer.ie/books/agent-architectures/04-chapter/</link>
      <pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate>
      <guid>http://programmer.ie/books/agent-architectures/04-chapter/</guid>
      <description>&lt;h3 id=&#34;the-goal&#34;&gt;The Goal&lt;/h3&gt;&#xA;&lt;p&gt;In this chapter, you will build your first small agentic system without writing code.&lt;/p&gt;&#xA;&lt;p&gt;You will do it in an ordinary chat interface, even on your phone. The point is not that a chat thread is the final form of an agent platform. The point is that the core architecture from Chapter 3 can be practiced in plain language:&lt;/p&gt;&#xA;&lt;div class=&#34;highlight&#34;&gt;&lt;pre tabindex=&#34;0&#34; style=&#34;color:#f8f8f2;background-color:#272822;-moz-tab-size:4;-o-tab-size:4;tab-size:4;&#34;&gt;&lt;code class=&#34;language-text&#34; data-lang=&#34;text&#34;&gt;&lt;span style=&#34;display:flex;&#34;&gt;&lt;span&gt;role&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span style=&#34;display:flex;&#34;&gt;&lt;span&gt;  ↓&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span style=&#34;display:flex;&#34;&gt;&lt;span&gt;task&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span style=&#34;display:flex;&#34;&gt;&lt;span&gt;  ↓&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span style=&#34;display:flex;&#34;&gt;&lt;span&gt;step&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span style=&#34;display:flex;&#34;&gt;&lt;span&gt;  ↓&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span style=&#34;display:flex;&#34;&gt;&lt;span&gt;tool-like action&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span style=&#34;display:flex;&#34;&gt;&lt;span&gt;  ↓&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span style=&#34;display:flex;&#34;&gt;&lt;span&gt;memory log&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span style=&#34;display:flex;&#34;&gt;&lt;span&gt;  ↓&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span style=&#34;display:flex;&#34;&gt;&lt;span&gt;reflection&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span style=&#34;display:flex;&#34;&gt;&lt;span&gt;  ↓&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span style=&#34;display:flex;&#34;&gt;&lt;span&gt;revision&#xA;&lt;/span&gt;&lt;/span&gt;&lt;/code&gt;&lt;/pre&gt;&lt;/div&gt;&lt;p&gt;This exercise builds a research assistant with a Manager role, a Researcher role, a visible Knowledge Log, and a review step.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
