---
title: "Building AI Agents that actually work (Full Course)"
source_url: https://youtu.be/eA9Zf2-qYYM
captured_at: 2026-03-20
author: "Greg Isenberg"
contributor: "ชิดชนก"
platform: youtube
---
# Building AI Agents that actually work (Full Course)

youtube video by **Greg Isenberg**, 58m55s, uploaded 2026-03-17. URL: https://youtu.be/eA9Zf2-qYYM
Tags: startup ideas, sip, entrepreneur podcast, business ideas, business trends, entrepreneur advice, business advice, greg isenberg, my first million, a16z, starter story, 1 million business, saas startup, startup advice, ai startup, ai business, ai startup idea, no code tools, AI Code, google ai, google gemini, ai tech stack, gemini, nano banana, ai, Google gemini 3, claude code, claude, claude skills

## Shared in LINE Note+
- 2026-03-20 17:21 by ชิดชนก — nearby chat: การติดตามสมาชิก เติมพืช พื้นที่ที่ขาดไป โทรติดตามสอบถามและบันทึก  ยกตัวอย่างกรณีนี้ ปลูกข้าว 100 ไร่ แต่แจ้งว่าซื้อปุ๋ยหัวเสือไปแล้ว

## Description
I sit down with Remy Gaskell to break down how anyone can build AI agents to run entire departments of their business. Remy walks through the core concepts: agent loops, context files, memory, MCP tool connections, and skills. We put everything together by building a fully functional executive assistant live on screen. This is a beginner-friendly crash course that covers Claude Code, Codex, Cowork, Antigravity, Manus, and OpenClaw, showing that once you understand how to "drive," you can jump into any agent platform. By the end, listeners know exactly how to set up markdown-based context files, connect their everyday tools, and create reusable skills that compound over weeks and months.

Timestamps
00:00 – Intro
01:35 – Agents vs Chat
03:22 – The Agent Loop
05:46 – How Agents work
06:39 – Demoing Agents (Claude Code, Codex, Antigravity)
08:52 – Security and Agent Permissions
10:43 – Comparing Results Across Three Platforms
13:57 – Startup Idea: Cold Email Website Offer
14:50 – Folder Structure and Department-Based Agents
15:52 – Onboarding an Agent Like a Real Employee
17:05 – Voice-to-Text With Monologue and WhisperFlow
18:04 – Chat Memory vs. Agent Memory
19:34 – Building the age
