Opinion certainty 3/5 debate potential 2/5

Gaskill: Claude Code displays agent loops best among major harnesses

Remy Gaskill · Building AI Agents that actually work (Full Course) · Mar 17, 2026 · at 11:19

Remy Gaskill compares agent execution across Claude Code, Google Antigravity, and OpenAI Codex during a live demo building a personal website.

0:00 / 0:12exact quote · 12.9s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“I think Claude code does the best job of actually displaying that loop and allowing you to see what it's thought about compared to anti-gravity and codex, but it's all just going through the same sort of loop process that I described earlier.”

quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →

More from Remy Gaskill

Prediction Not checkable as stated
Gaskill: People will stop using SaaS apps directly in favor of AI operating systems
“I think that everyone's gonna have, like, an AI operating system they work in, and everyone will just have personal agents and agents to manage each department of their company, and people won't actually use these apps anymore.”
Remy Gaskill Mar 17, 2026 ▶ 35:22 Building AI Agents that actually work (Full Course)
Insight
Gaskill: AI optimization shifted from prompt engineering to context engineering
“Prompt engineering used to be the big thing. It was like, here's the ultimate prompt for going viral on social media, or use this prompt for this. And now it's all about context engineering. It's about how well can you load up your agent with all the informati…”
Remy Gaskill Mar 17, 2026 ▶ 22:02 Building AI Agents that actually work (Full Course)
Assertion Not checkable as stated
Gaskill: Founders using AI agents are 10 to 20 times more productive
“The founders and employees that are utilizing agents are like, no word of a lie, 10 to 20 times more productive in their day.”
Remy Gaskill Mar 17, 2026 ▶ 1:52 Building AI Agents that actually work (Full Course)
Opinion
Gaskill: Manual agent memory setup is superior to automatic chat memory
“And with agents, you have to set up memory and control exactly what you give it. And I think that's actually a benefit, not a limitation, because what happens is if you're using ChatGPT and it's got the auto memory, you're having conversations about three diff…”
Remy Gaskill Mar 17, 2026 ▶ 18:40 Building AI Agents that actually work (Full Course)
Opinion
Gaskill: Future-proof AI stacks rely on local markdown files
“The real future-proof AI stack is just having those markdown files on your computer.”
Remy Gaskill Mar 17, 2026 ▶ 34:15 Building AI Agents that actually work (Full Course)
Insight
Gaskill: Popular AI Agent Platforms Are Merely Agent Harnesses
“And all of the popular AI agent platforms on the market that you'd be familiar with are just agent harnesses. They're just applications where this loop is facilitated.”
Remy Gaskill Mar 17, 2026 ▶ 6:28 Building AI Agents that actually work (Full Course)
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 300 episodes transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.