DESCRIPTION
Jack Rudenko hasn't written a line of code himself in nine months. In that time, his team has shipped six or seven products used by millions of people, and he says that gap, between who writes the code and who's actually building, is the whole story of engineering right now.
In this episode of Building Tech Teams, James MacDonald sits down with Jack Rudenko, Partner and Chief AI and Technical Strategist at 10x Labs, where he has spent the past two years building an AI-native engineering practice from the ground up. They get into the project everyone called impossible before AI made it a three-month build, why working with AI agents is more exhausting than writing code ever was, and what actually separates an engineer from an artist or a scientist now that the code itself isn't the hard part.
It's a hands-on, practitioner's take on what building with AI agents actually looks like day to day, not the conference-keynote version. They cover Jack's own workflow for briefing an AI agent, why he doesn't trust any project's security the moment an API key exists, the "non-engineering builders" quietly out-building agencies, and why he calls Claude Code some of the worst-engineered software he's ever used, and also the tool he loves most.
CHAPTERS
0:00 - Cold open: the line that explains why most AI engineering doesn't work
0:31 - Who Jack Rudenko is, and what's ahead in this episode
1:27 - Welcome, meet Jack Rudenko, Chief AI and Technical Strategist at 10x Labs
1:48 - The real bottleneck in AI engineering is human, not technical
3:36 - Why "AI native from scratch" beats bolting AI onto old processes
8:53 - Inside Magus, treating AI skills like versioned software packages
11:20 - 500 skills later, building a curated knowledge base for AI agents
14:56 - The rise of the "non-engineering builder"
17:06 - Why enterprise software is the real mess, not startups
19:32 - The unexpected cost of working with AI, burnout, not laziness
21:24 - Jack's actual workflow, plan mode, research, and acceptance criteria
27:26 - Dark factories, evals, and "religion" versus "engineering" in AI
29:49 - The skill nobody measured, loaded less than half the time
32:52 - Why AST trees beat graph databases for AI code memory
36:07 - From 10X to 50X, two projects AI made possible
41:35 - What team size looks like when one person can do it all
42:53 - Why no project is secure once a key exists
46:44 - Artist, scientist, engineer, what actually makes you one
51:04 - What junior engineers need to learn now
54:45 - Cursor, YC founders, and the rise of the non-engineer builder
59:35 - The addictive, exhausting superpower of building 10X more
1:02:57 - Why "impossible" projects are worth the budget now
1:04:55 - The future of software, giant platforms and a million small ones
1:08:04 - Why consultancies are thriving, for now
1:09:12 - "Claude Code is the worst software ever. I love it."
1:11:22 - Open source, Jack's origin story, and why it built him
1:15:23 - James's takeaway: religion vs engineering, and the challenge to measure your own AI rollout
ABOUT THE GUEST
Jack Rudenko is Partner and Chief AI and Technical Strategist at 10x Labs, where he has spent the past two years building the team's AI-native engineering practice, Magus, from the ground up. He has deep expertise in cloud-native architecture, Go, Kubernetes and complex systems, and has delivered production platforms that would have been considered technically impossible before AI, including a three-system integration project used as a case study on this episode. Jack is also a longtime open-source contributor, including to the Linux kernel.
LINKS
Jack Rudenko, 10x Labs · LinkedIn: https://www.linkedin.com/in/erudenko/
James MacDonald, NTP Talent · LinkedIn: linkedin.com/in/jamesmacdonaldau · Site: ntptalent.com.au
Hosted by James MacDonald, Managing Director of NTP Talent.
---
Building Tech Teams is produced by Day One®, trusted partners in the technology space and the production partner behind Blackbird Ventures' Wild Hearts. Sister shows include First Cheque, Oversubscribed and In The Blink of AI. Episodes are cross-promoted across the network.
