Humility in the Age of Agentic Coding
Episode
55 min
Read time
2 min
Topics
Productivity, Relationships, Investing
AI-Generated Summary
Key Takeaways
- ✓Agentic coding as a learnable skill: Treating AI-assisted development like Vim — a tool with a real learning curve — changes outcomes significantly. Klabnik's first Roo attempt failed partly due to his own inexperience with agentic workflows. His second attempt, with better prompting habits and tighter iteration loops, produced dramatically higher code quality and velocity.
- ✓Validation-first development unlocks agent performance: Klabnik built a custom test framework that connects a formal language specification directly to runnable test cases before writing compiler code. This gave Claude a concrete pass/fail signal to iterate toward, replacing manual review cycles. Agents converge on correctness faster when given automated, objective evaluation criteria rather than human spot-checks.
- ✓DRY and clean code conventions are human-centric heuristics: Many software engineering practices — avoiding code duplication, tab-width debates, microservice boundaries — exist to manage human cognitive limits, not machine ones. Klabnik now tolerates five identical function copies in a codebase, trusting that Claude can identify and consolidate them in seconds when it matters, rather than enforcing it upfront.
- ✓Non-programmers model AI uncertainty better than developers do: Klabnik's observation: software engineers are trained on determinism and treat hallucination as disqualifying. Non-technical users already expect computers to be partially wrong and fact-check outputs by default. Developers who adopt that same verification-first mindset — treating AI output as a draft, not a result — extract more practical value from the tools.
- ✓The unsolved problem is trust at merge velocity: Klabnik shipped roughly 100 pull requests on Christmas Day while with family, reviewing each diff in seconds rather than minutes. The productivity gain is real but the quality risk is unresolved. He frames this as the central engineering question of 2026: how to establish sufficient trust in agentic output to allow fast merging without accumulating dangerous technical debt.
What It Covers
Steve Klabnik, Rust programming language contributor and author, traces his shift from AI skeptic to agentic coding practitioner. He details building the Roo programming language almost entirely with Claude, examines which software engineering beliefs hold up under AI-assisted development, and identifies the central unsolved problem of maintaining code quality at machine velocity.
Key Questions Answered
- •Agentic coding as a learnable skill: Treating AI-assisted development like Vim — a tool with a real learning curve — changes outcomes significantly. Klabnik's first Roo attempt failed partly due to his own inexperience with agentic workflows. His second attempt, with better prompting habits and tighter iteration loops, produced dramatically higher code quality and velocity.
- •Validation-first development unlocks agent performance: Klabnik built a custom test framework that connects a formal language specification directly to runnable test cases before writing compiler code. This gave Claude a concrete pass/fail signal to iterate toward, replacing manual review cycles. Agents converge on correctness faster when given automated, objective evaluation criteria rather than human spot-checks.
- •DRY and clean code conventions are human-centric heuristics: Many software engineering practices — avoiding code duplication, tab-width debates, microservice boundaries — exist to manage human cognitive limits, not machine ones. Klabnik now tolerates five identical function copies in a codebase, trusting that Claude can identify and consolidate them in seconds when it matters, rather than enforcing it upfront.
- •Non-programmers model AI uncertainty better than developers do: Klabnik's observation: software engineers are trained on determinism and treat hallucination as disqualifying. Non-technical users already expect computers to be partially wrong and fact-check outputs by default. Developers who adopt that same verification-first mindset — treating AI output as a draft, not a result — extract more practical value from the tools.
- •The unsolved problem is trust at merge velocity: Klabnik shipped roughly 100 pull requests on Christmas Day while with family, reviewing each diff in seconds rather than minutes. The productivity gain is real but the quality risk is unresolved. He frames this as the central engineering question of 2026: how to establish sufficient trust in agentic output to allow fast merging without accumulating dangerous technical debt.
Notable Moment
Klabnik describes how Fred Brooks' foundational rule — adding developers slows a project down — may no longer hold in agentic workflows. OpenAI's internal data on agent-assisted development reportedly showed the opposite effect, with more contributors increasing velocity rather than reducing it.
Episode Transcript
Welcome to the Practical AI podcast, where we break down the real world applications of artificial intelligence and how it's shaping the way we live, work, and create. Our goal is to help make AI technology practical, productive, and accessible to everyone. Whether you're a developer, business leader, or just curious about the tech behind the buzz, you're in the right place. Be sure to connect with us on LinkedIn, x, or Blue Sky to stay up to date with episode drops, behind the scenes content, and AI insights. You can learn more at practicalai.fm. Now onto the show. Welcome to another episode of the Practical AI podcast. Podcast. This is Daniel Whitenak. I am CEO at Prediction Guard, and I'm joined as always by my cohost, Chris Benson, who's a principal AI and autonomy research engineer. How are you doing, Chris? Doing great. Enjoying, having fun, and and, gosh, gosh, the weather, where I'm at is awesome. So, like Yeah. Yeah. I had to I had to force myself to come in to do the show today. So Yeah. Yeah. I unfortunately had a a mild case of of COVID last week. And so coming into this week, it's both, like, really nice weather, and I'm over that. So I feel, like, extra boost. Welcome back. Yeah. Thanks. Thanks. It's good to be back. And, and, yeah, for our listeners, just one thing you might wanna be aware of. If you are in the San Francisco area or if you're attending RSA, I'm gonna be at the conference at at RSA, out in San Francisco March 2026. If you're listening to this years later, I won't potentially be there years later, but this year, I'll this year, I'll be there. And, and I do have, like, some some meeting space where I can meet up with people if you wanna talk about enterprise y AI things, or I'm gonna have some demos on, like, you know, AI build materials and some cool prompt injection stuff. So if you're if you're into that side of things from the security enterprise AI side, I'll I'll include the link in the show notes if people wanna figure out where to find me or or, find a time. So, look me up there. But, really, excited to to get into the conversation today. We have, an amazing guest with us, who I'm I'm excited to get to know a little bit. Really intrigued by his work, Steve Klavnik, who is a software engineer. And I'll leave it up to you, Steve. Maybe you can you can describe why Software engineer extraordinary. Software engineer extraordinary, how you ended up on a on a AI podcast, what what your background is, and, how where that intersects with AI, I guess. Yeah. Thanks, guys. I, thanks for having me. It's it's good to be here. And, yeah. I have, like, a weird background, and so I never know what to say with these kind of things. …
Get the full transcript (12,033 words) + summary by email — free
One-time email with the complete transcript and AI summary of this episode. No account needed.
One email, no spam. We’ll also show you what SignalCast does.
You just read a 3-minute summary of a 52-minute episode.
Get Practical AI summarized like this every Monday — plus up to 2 more podcasts, free.
Pick Your Podcasts — FreeKeep Reading
More from Practical AI
Computer-Use Agents and the Future of the Agentic Internet
Sep 10 · 56 min
The School of Greatness
Former Secret Service Agent Reveals How to Read Anyone
Nov 19
More from Practical AI
Less about Models; More about Architecture
Sep 3 · 45 min
The Vergecast
Schools are catching onto tech’s playbook
Sep 10
Books, tools, and gear mentioned in this episode
SignalCast may earn commission on purchases via these links. As an Amazon Associate, SignalCast earns from qualifying purchases.
Books

by Fred Brooks
“Klabnik describes how Fred Brooks' foundational rule — adding developers slows a project down — may no longer hold in agentic workflows.”
Tools
- ClaudeRecommended
by Anthropic
“He details building the Roo programming language almost entirely with Claude, examines which software engineering beliefs hold up under AI-assisted development.”
- VimRecommended
“Treating AI-assisted development like Vim — a tool with a real learning curve — changes outcomes significantly.”
“SPONSORS: Prediction Guard (https://predictionguard.com)”
other
- RooBy guest
by Steve Klavnik
“He details building the Roo programming language almost entirely with Claude.”
More from Practical AI
We summarize every new episode. Want them in your inbox?
Computer-Use Agents and the Future of the Agentic Internet
Less about Models; More about Architecture
Building the Foundation for the Agentic AI Era
AI Proficiency: From Users to Builders
Models, Harnesses, and Multi-Agent Systems
Similar Episodes
Related episodes from other podcasts
The School of Greatness
Nov 19
Former Secret Service Agent Reveals How to Read Anyone
The Vergecast
Sep 10
Schools are catching onto tech’s playbook
Software Engineering Daily
Sep 10
A Rust Framework to Simplify Distributed Systems
Masters of Scale
Sep 10
From high school dropout to CEO, with Autodesk’s Andrew Anagnost
The Joe Rogan Experience
Sep 3
#2549 - Jared Diamond
Explore Related Topics
This podcast is featured in Best AI Podcasts (2026) — ranked and reviewed with AI summaries.
Read this week's Investing & Markets Podcast Insights — cross-podcast analysis updated weekly.
You're clearly into Practical AI.
Every Monday, we deliver AI summaries of the latest episodes from Practical AI and 192+ other podcasts. Free for one show.
Start My Monday DigestNo credit card · Unsubscribe anytime