AI Summary
5 min read🎙️ The Voices & The Context
- The Format: Casual interview with live demos – host guides guest through a beginner-friendly tutorial on AI agents, switching tabs for real-time builds.
- The Key Players:
- Guest: Remy Gaskill (AI expert who runs his company via AI agents; built viral tools like a Meta ads manager agent).
- Host: Greg Isenberg (podcaster excited about AI productivity; uses demos featuring himself).
- The Vibe: Educational & Exciting – geeky enthusiasm over AI demos, with "mind-blown" reactions and productivity hype.
🗝️ Key Themes & Topics
Remy delivers a crash course on AI agents to supercharge beginners, shifting from chatbots to autonomous "employees." Core shift: chat models (Q&A ping-pong) vs. agents (goal → result via loops).
- Topic 1: Agent Fundamentals. Chat is question-answer; agents use an observe-think-act loop in agent harnesses (e.g., Claude Code, Codex, Anti-Gravity) until tasks complete. LLM brain + tools + context = magic.
- Topic 2: Onboarding Agents. Create agents.md (system prompt with your bio/business prefs) and memory.md (self-updating prefs like "sign emails 'Warm Regards'") for persistent smarts.
- Topic 3: Tools & MCPs. MCP (Model Context Protocol) translates AI to apps (Gmail, Notion). Connect via harness settings for unified workflows – no app-switc
Continue reading the full summary in the app — free to try.
Read Full Summary →Free • No credit card required
What you'll learn
- 1 (00:00) **🎙️ Introduction: Remy Gaskills**
- 2 (01:36) **Chat Models vs. AI Agents**
- 3 (03:40) **The Agent Loop: Observe, Think, Act**
- 4 (06:39) **Live Demo: Building a Portfolio Website**
- 5 (15:17) **Building an Executive Assistant Agent**
- 6 (19:21) **Context Engineering: agents.md Files**
- 7 (24:34) **Agent Memory: memory.md Files**
+ Full timestamped outline available in the app
Show Notes
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 agents md
22:20 – Context Engineering Over Prompt Engineering
24:29 – How Memory Compounds and Reduces Errors
30:27 – How Big Can memory md Get?
31:43 – Connecting Tools via MCP (Model Context Protocol)
34:49 – Working in Claude Code for High-Value Tasks
37:09 – Why the Real Value Is in Stacking, Not Summarizing
40:04 – What Are Skills? (SOPs for AI)
43:08 – Creating Skills
48:36 – Real-World Example: Ads Analyst Skill: 4-Hour Process in Minutes
50:37 – Chaining Skills together
52:01 – Real-World Example: Automated Car Search
53:34 – OpenClaw and Migrating Agents to More Autonomous Platforms
55:19 – Which Platform Should Beginners Start With?
56:28 – Global vs. Project-Level Skills, Context, and MCPs
Key Points
Agent platforms (Claude Code, Codex, Cowork, Antigravity, Manus, OpenClaw) are all running the same observe-think-act loop under the hood — learning one means you can use any of them.
The
More from this podcast
The Startup Ideas Podcast →