4 lines
5.2 KiB
JavaScript
4 lines
5.2 KiB
JavaScript
import{c as e,Q as a,j as s,m as n}from"./chunks/framework.BPKcPtvA.js";const p=JSON.parse('{"title":"Free Preview: Lesson 1.1 — What Makes an Agent?","description":"","frontmatter":{},"headers":[],"relativePath":"free-preview.md","filePath":"free-preview.md","lastUpdated":1780491906000}'),o={name:"free-preview.md"};function i(r,t,d,l,h,c){return a(),s("div",null,[...t[0]||(t[0]=[n(`<h1 id="free-preview-lesson-1-1-—-what-makes-an-agent" tabindex="-1">Free Preview: Lesson 1.1 — What Makes an Agent? <a class="header-anchor" href="#free-preview-lesson-1-1-—-what-makes-an-agent" aria-label="Permalink to "Free Preview: Lesson 1.1 — What Makes an Agent?""></a></h1><p>This is a sample lesson from <strong>Module 1: Foundations</strong> of the FDSA Agentic Engineering Course. Full course includes 65 lessons, 13 labs, and 20 skill kits.</p><hr><h2 id="lesson-1-1-what-makes-an-agent" tabindex="-1">Lesson 1.1: What Makes an Agent? <a class="header-anchor" href="#lesson-1-1-what-makes-an-agent" aria-label="Permalink to "Lesson 1.1: What Makes an Agent?""></a></h2><p><strong>Definition</strong>: An AI agent = LLM + Tools + Loop. Without any one of these three, it's not an agent.</p><div class="language- vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang"></span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span>Agent = LLM (reasoning engine)</span></span>
|
||
<span class="line"><span> + Tools (capability surface)</span></span>
|
||
<span class="line"><span> + Loop (autonomous decision cycle)</span></span></code></pre></div><ul><li>A single LLM call with no tools = chatbot</li><li>An LLM with tools but no loop = augmented inference</li><li>Tools + loop + LLM = agent (it can decide what to do next)</li></ul><h3 id="the-three-components" tabindex="-1">The Three Components <a class="header-anchor" href="#the-three-components" aria-label="Permalink to "The Three Components""></a></h3><p><strong>LLM</strong> — The reasoning engine. Given context + available tools, it decides which tool to call and with what parameters. The LLM is NOT the agent — it's the brain of the agent. Different models have different reasoning capabilities, but the core function is the same: given a situation and available actions, decide what to do.</p><p><strong>Tools</strong> — The capability surface. Functions the agent can call: read files, run commands, search the web, query databases, call APIs. Each tool has a name, description, and input schema. The tool surface defines what the agent CAN do — everything outside this surface is something the agent cannot do, no matter how smart the LLM is.</p><p><strong>Loop</strong> — The autonomous decision cycle. Think (LLM decides) → Act (tool executes) → Observe (result comes back) → Repeat. The loop is what makes it autonomous. Without a loop, you have a single decision. With a loop, you have an agent that can work toward a goal across multiple steps.</p><h3 id="why-this-matters" tabindex="-1">Why This Matters <a class="header-anchor" href="#why-this-matters" aria-label="Permalink to "Why This Matters""></a></h3><p>This definition is not academic. Every production agent failure I've seen traces back to one of these three:</p><table tabindex="0"><thead><tr><th>Failure</th><th>Root Cause</th></tr></thead><tbody><tr><td>Agent does something unexpected</td><td>Loop didn't terminate correctly</td></tr><tr><td>Agent can't do the task</td><td>Tools are insufficient for the task</td></tr><tr><td>Agent makes bad decisions</td><td>LLM doesn't have enough context</td></tr><tr><td>Agent costs too much</td><td>Loop runs too many iterations</td></tr></tbody></table><p>If you understand these three components and how they interact, you can debug any agent system. If you don't, you're guessing.</p><hr><h2 id="what-you-ll-learn-in-the-full-course" tabindex="-1">What You'll Learn in the Full Course <a class="header-anchor" href="#what-you-ll-learn-in-the-full-course" aria-label="Permalink to "What You'll Learn in the Full Course""></a></h2><table tabindex="0"><thead><tr><th>Module</th><th>Topic</th><th>Lessons</th><th>Labs</th></tr></thead><tbody><tr><td>M1</td><td>Foundations</td><td>8 lessons</td><td>1 lab</td></tr><tr><td>M2</td><td>Agent Architecture</td><td>7 lessons</td><td>2 labs</td></tr><tr><td>M3</td><td>Safety & Security</td><td>7 lessons</td><td>2 labs</td></tr><tr><td>M4</td><td>Multi-Agent Orchestration</td><td>11 lessons</td><td>2 labs</td></tr><tr><td>M5</td><td>Production Systems</td><td>10 lessons</td><td>2 labs</td></tr><tr><td>M6</td><td>Model Economics</td><td>7 lessons</td><td>2 labs</td></tr><tr><td>M7</td><td>Advanced Patterns</td><td>8 lessons</td><td>2 labs</td></tr><tr><td>M8</td><td>Capstone Project</td><td>—</td><td>Build & deploy</td></tr></tbody></table><p><a href="/buy">Enroll Now — $97</a> · <a href="/modules/curriculum">View Full Curriculum</a></p><p><em>Note: This preview shows approximately 30% of a single lesson. Full lessons include code examples, diagrams, quiz questions, and lab exercises.</em></p>`,20)])])}const g=e(o,[["render",i]]);export{p as __pageData,g as default};
|