Carson: AI agents should compound intelligence from mistakes via markdown memory files
Ryan Carson · "Ralph Wiggum" AI Agent will 10x Claude Code/Amp · Jan 8, 2026 · at 17:32
Ryan Carson discusses autonomous AI agent architectures with Greg Isenberg, explaining Every's 'compound engineering' concept where agents write persistent learnings to local markdown files.
0:00 / 0:14exact quote · 14.4s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“Your agent should be getting smarter every time it makes a mistake. And by updating agents.md, you are going to get that long-term benefit. This isn't just during this iteration. You're going to benefit every time from now on that you use amp or clog code.”
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 Ryan Carson
Carson: Engineers coding locally are cavemen shipping 10x less code
“So I think if you are working locally, I honestly think you are a caveman. Like, I think you're, you are holding yourself back, and you are shipping 10 X less than you could be, and it is not smart. No matter if you think the cool people work locally and all t…”
Carson: The AI agent era requires working more, not less
“And in in order to survive in this new world, you're going to work a lot more, not a lot less.”
Carson warns against building workflows on frontier models to avoid lock-in
“Like, if you are, if your whole engineering you know, motion is happening inside of clock code or inside of codex, What are you doing? Like, because they are not incentivized to make it reasonable for you long term, right? They're going to lock you into their …”
Carson: AI agents will write, review, and ship 100% of code
“You will be using a software factory. Like, and what I mean is, the agents are going to be writing a hundred percent of your code, reviewing a hundred percent of your code, shipping a hundred percent of your code. Like, that's where we're going.”
Carson: Ralph AI loop functions as an entire engineering team overnight
“This loop is basically an entire engineering team while you sleep. It's unbelievable. And this just wasn't possible for Opus four or five. I think with Opus four or five, this is absolutely The real deal.”
Carson: AI engineering token costs will hit $5,000 monthly per employee
“I think all of us are in a place where we, we're getting to the spot where it's realizing, okay, for real engineering work per employee, you're looking at probably five grand a month. Like, that's probably where we're gonna shake out here.”