AI-Assisted Coding: Why a Distinguished Engineer Stopped Reading Code — Lights-Out Codebases and the End of the IC

Philip Su has spent two decades at the highest levels of software engineering — Microsoft, Meta (where he reached Distinguished Engineer, IC9), OpenAI, and now building his own product solo with AI. In this episode, he makes a provocative case: the individual contributor role as we know it is over, code reviews are becoming a liability, and the best engineers are already managing AI agents instead of writing code themselves.

From Dirty Fuel to Clean Fuel — Philip’s Unusual Career Arc

“When I look at those employment opportunities, I feel like maybe one theme is moving from what people are calling dirty fuel into clean fuel — meaning, what sorts of things motivate you? Dirty fuel would be something like, my parents never complimented me and so now I’m going to drive and prove them wrong. Clean fuel would be, I’ve always loved computer science and I’m here to do it.”

Philip’s path through tech is anything but linear. He became a dev manager at Microsoft before 30, then spent the next decade comfortable but stagnating — until he interviewed at Google, Amazon, and Meta and received offers three levels below his Microsoft position. That fear drove him to Facebook in 2010, when it had just 500 employees and people were still saying Friendster would come back. He scaled the London engineering office from a dozen engineers to 500+, then stepped away entirely.

Depression led him to take a warehouse floor job at Amazon during Peak 2021 — 11-hour shifts, moving six tons of packages a day with his arms. He documented the experience in his Peak Salvation podcast. The lessons were sharp: incentives shape behavior (warehouse workers got raises based on tenure, not performance, which incentivized doing the minimum), changing machines that are already operating is brutally hard, and misplaced pride is dangerous. Workers on the floor laughed when robots failed. Philip’s takeaway was the opposite: “Do you think the corporate robot designers just gave up and went home? Or do you think V2 is coming and V3 is coming until finally it takes over your job?” He later joined OpenAI as an individual contributor before leaving to build Superphonic, an AI-powered podcast player.

No More Code Reviews: The Lights-Out Codebase

“I grew up in the 80s and 90s. Today, even Stockfish, free on your phone, can beat the world’s best chess masters. What if I proposed to you today that you should take that free software, and when you’re playing some other player, have a human chess master review every move, just to make sure the AI hasn’t made a mistake? I would think that was patently ridiculous.” Continue reading AI-Assisted Coding: Why a Distinguished Engineer Stopped Reading Code — Lights-Out Codebases and the End of the IC

AI Assisted Coding: AI as an Amplifier—Why Engineering Practices Matter More Than Ever

AI Assisted Coding: How Spending 4x More on Code Quality Doubled Development Speed

What happens when you combine nearly 30 years of engineering experience with AI-assisted coding? In this episode, Eduardo Ferro shares his experiments showing that AI doesn’t replace good practices—it amplifies them. The result: doubled productivity while spending four times more on code quality.

Vibe Coding vs Production-Grade AI Development

“Vibe coding is flow-driven, curiosity-based way of building software with AI. It’s less about meticulously reviewing each line of code, and more about letting the AI steer the process—perfect for quick experiments, side projects, MVPs, and prototypes.”

Edu draws a clear distinction between vibe coding and production AI development. Vibe coding is exploration-focused, where you let AI drive while you learn and discover. Production AI coding is goal-focused, with careful planning, spec definition, and identification of edge cases before implementation. Both use small, safe steps and continuous conversation with the AI, but production code demands architectural thinking, security analysis, and sustainability practices. The key insight is that even vibe coding benefits from engineering discipline—as experiments grow, you need sustainable practices to maintain flexibility.

How AI Doubled My Productivity

“I was investing four times more in refactoring, cleanup, deleting code, introducing new tests, improving testability, and security analysis than in generating new features. And at the same time, globally, I think I more or less doubled my pace of work.” Continue reading AI Assisted Coding: AI as an Amplifier—Why Engineering Practices Matter More Than Ever

AI Assisted Coding: Augmented AI Development – Software Engineering First, AI Second

In this special episode, Dawid Dahl introduces Augmented AI Development (AAID)—a disciplined approach where professional developers augment their capabilities with AI while maintaining full architectural control. He explains why starting with software engineering fundamentals and adding AI where appropriate is the opposite of most frameworks, and why this approach produces production-grade software rather than technical debt.

The AAID Philosophy: Don’t Abandon Your Brain

“Two of the fundamental developer principles for AAID are: first, don’t abandon your brain. And the second is incremental steps.”

Dawid’s Augmented AI Development framework stands in stark contrast to “vibecoding“—which he defines strictly as not caring about code at all, only results on screen. AAID is explicitly designed for professional developers who maintain full understanding and control of their systems. The framework is positioned on the furthest end of the spectrum from vibe coding, requiring developers to know their craft deeply. The two core principles—don’t abandon your brain, work incrementally—reflect a philosophy that AI is a powerful collaborator, not a replacement for thinking. This approach recognizes that while 96% of Dawid’s code is now written by AI, he remains the architect, constantly steering and verifying every step.

In this segment we refer to Marcus Hammarberg’s work and his book The Bungsu Story.

Software Engineering First, AI Second: A Hill to Die On

“You should start with software engineering wisdom, and then only add AI where it’s actually appropriate. I think this is super, super important, and the entire foundation of this framework. This is a hill I will personally die on.”

What makes AAID fundamentally different from other AI-assisted development frameworks is its starting point. Most frameworks start with AI capabilities and try to add structure and best practices afterward. Dawid argues this is completely backwards. AAID begins with 50-60 years of proven software engineering wisdom—test-driven development, behavior-driven development, continuous delivery—and only then adds AI where it enhances the process. This isn’t a minor philosophical difference; it’s the foundation of producing maintainable, production-grade software. Dawid admits he’s sometimes “manipulating developers to start using good, normal software engineering practices, but in this shiny AI box that feels very exciting and new.” If the AI wrapper helps developers finally adopt TDD and BDD, he’s fine with that.

Why TDD is Non-Negotiable with AI

“Every time I prompt an AI and it writes code for me, there is often at least one or two or three mistakes that will cause catastrophic mistakes down the line and make the software impossible to change.” Continue reading AI Assisted Coding: Augmented AI Development – Software Engineering First, AI Second

AI Assisted Coding: Swimming in AI – Managing Tech Debt in the Age of AI-Assisted Coding

In this special episode, Lou Franco, veteran software engineer and author of “Swimming in Tech Debt,” shares his practical approach to AI-assisted coding that produces the same amount of tech debt as traditional development—by reading every line of code. He explains the critical difference between vibecoding and AI-assisted coding, why commit-by-commit thinking matters, and how to reinvest productivity gains into code quality.

Vibecoding vs. AI-Assisted Coding: Reading Code Matters

“I read all the code that it outputs, so I need smaller steps of changes.”

Lou draws a clear distinction between vibecoding and his approach to AI-assisted coding. Vibecoding, in his definition, means not reading the code at all—just prompting, checking outputs, and prompting again. His method is fundamentally different: he reads every line of generated code before committing it. This isn’t just about catching bugs; it’s about maintaining architectural control and accountability. As Lou emphasizes, “A computer can’t be held accountable, so a computer can never make decisions. A human always has to make decisions.” This philosophy shapes his entire workflow—AI generates code quickly, but humans make the final call on what enters the repository. The distinction matters because it determines whether you’re managing tech debt proactively or discovering it later when changes become difficult.

The Moment of Shift: Staying in the Zone

“It kept me in the zone. It saved so much time! Never having to look up what a function’s arguments were… it just saved so much time.”

Lou’s AI coding journey began in late 2022 with GitHub Copilot‘s free trial. He bought a subscription immediately after the trial ended because of one transformative benefit: staying in the flow state. The autocomplete functionality eliminated constant context switching to documentation, Stack Overflow searches, and function signature lookups. This wasn’t about replacing thinking—it was about removing friction from implementation. Lou could maintain focus on the problem he was solving rather than getting derailed by syntax details. This experience shaped his understanding that AI’s value lies in removing obstacles to productivity, not in replacing the developer’s judgment about architecture and design.

Thinking in Commits: The Right Size for AI Work

“I think of prompts commit-by-commit. That’s the size of the work I’m trying to do in a prompt.” Continue reading AI Assisted Coding: Swimming in AI – Managing Tech Debt in the Age of AI-Assisted Coding

Dave Smith: Democratizing Leadership, Cultivating a Culture of Openness and Improvement in Open Source Agile Teams

“Leadership is not about titles, it’s about action.” Dave’s story on change leadership dismantles the myth of hierarchical leadership, advocating for a culture where anyone can step up. By introducing version control in a volunteer group riddled with anti-patterns, Dave demonstrates how leading by example and involving stakeholders in change processes can foster a positive approach to code quality and project management. Learn how creating psychological safety and inviting feedback can turn the most ardent resisters into advocates for change.

Want to Improve Your Change Management Results? Discover the Lean Change Management Approach Today!

As Scrum Master we work with change continuously! Do you have your own change framework that provides the guidance, and queues you need when working with change? The Lean Change Management framework is a fully defined, lean-startup inspired change framework that can be used as the backbone of any change process! You can buy Lean Change Management the book at Amazon. Also available in French, Spanish, German and Portuguese.

About Dave Smith

Dave, has over 20 years in training and consulting, having taught Scrum he continues to be active in the agile community, mentoring and helping others who are joining the agile community.

You can link with Dave Smith on LinkedIn.