<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Agent Foundations on DATATWEETS</title><link>https://datatweets.com/courses/ai-agents/agent-foundations/</link><description>Recent content in Agent Foundations on DATATWEETS</description><generator>Hugo</generator><language>en</language><copyright>Copyright (c) 2025 Datatweets</copyright><lastBuildDate>Sun, 28 Jun 2026 09:00:00 +0200</lastBuildDate><atom:link href="https://datatweets.com/courses/ai-agents/agent-foundations/index.xml" rel="self" type="application/rss+xml"/><item><title>Lesson 1 - What Is an Agent?</title><link>https://datatweets.com/courses/ai-agents/agent-foundations/lesson-1-what-is-an-agent/</link><pubDate>Fri, 19 Dec 2025 09:00:00 +0200</pubDate><guid>https://datatweets.com/courses/ai-agents/agent-foundations/lesson-1-what-is-an-agent/</guid><description>An agent isn&amp;rsquo;t a bigger prompt or a smarter model — it&amp;rsquo;s a language model placed in a loop where it chooses its own next action, uses tools, sees the results, and continues until the goal is reached. Learn the agent loop that everything else builds on.</description></item><item><title>Lesson 2 - Agents vs. Workflows</title><link>https://datatweets.com/courses/ai-agents/agent-foundations/lesson-2-agents-vs-workflows/</link><pubDate>Fri, 19 Dec 2025 09:00:00 +0200</pubDate><guid>https://datatweets.com/courses/ai-agents/agent-foundations/lesson-2-agents-vs-workflows/</guid><description>Workflows run a fixed path you coded; agents let the model decide each step at runtime. Learn the trade-offs and a four-part checklist — complexity, value, viability, and cost of error — for choosing an agent only when the task truly needs one.</description></item><item><title>Lesson 3 - The Anatomy of an Agent</title><link>https://datatweets.com/courses/ai-agents/agent-foundations/lesson-3-the-anatomy-of-an-agent/</link><pubDate>Fri, 19 Dec 2025 09:00:00 +0200</pubDate><guid>https://datatweets.com/courses/ai-agents/agent-foundations/lesson-3-the-anatomy-of-an-agent/</guid><description>Every agent is built from the same parts: a model, instructions, tools, the loop that runs them, memory, and stopping conditions. Learn what each does and how they compose into an agent, mapped onto the Atlas trip-planning agent you&amp;rsquo;ll build.</description></item><item><title>Lesson 4 - Your First Claude Call</title><link>https://datatweets.com/courses/ai-agents/agent-foundations/lesson-4-your-first-claude-call/</link><pubDate>Fri, 19 Dec 2025 09:00:00 +0200</pubDate><guid>https://datatweets.com/courses/ai-agents/agent-foundations/lesson-4-your-first-claude-call/</guid><description>Get from zero to a working Claude API call: install the anthropic SDK, store your API key as an environment variable, send a message with the model, system prompt, and messages, and read the text, stop reason, and token usage from the response.</description></item><item><title>Lesson 5 - Guided Project: Design the Atlas Agent</title><link>https://datatweets.com/courses/ai-agents/agent-foundations/lesson-5-guided-project-design-the-atlas-agent/</link><pubDate>Fri, 19 Dec 2025 09:00:00 +0200</pubDate><guid>https://datatweets.com/courses/ai-agents/agent-foundations/lesson-5-guided-project-design-the-atlas-agent/</guid><description>Apply everything from Module 1 to design Atlas, a trip-planning agent: define its goal and system prompt, justify it as an agent, sketch its tools, map its anatomy, and trace the decide-act-observe loop for a sample request.</description></item></channel></rss>