Beyond Coding

Jeroen Gordijn and Jeroen Dee: two frontrunners who stopped writing code months ago and say software development is already solved. Typing code is no longer necessary, but what matters more now? If you're an engineer that loves coding, you're in a tougher spot than you might realize.

In this video, we cover:
- Why writing code is "solved" but engineering isn't
- Spec-driven development and how to get it started in your team
- The "Dark Factory" and why code review is a huge bottleneck
- Model vs harness: what matters more, and why
- The unhealthy side of agentic coding

If you write software for a living and you're trying to work out what your job becomes next, start here.

Timestamps:
00:00:00 - Coding Is No Longer Necessary
00:00:43 - Why "Software Development Is Already Solved"
00:02:57 - Should You Even Read the AI's Code?
00:05:05 - What Is a "Dark Factory"?
00:06:52 - If You Can Regenerate It, Why Care About Quality?
00:07:49 - Spec-Driven Development Explained
00:11:32 - Adopting Specs Without Starting From Scratch
00:13:23 - Model vs Harness: What Matters More?
00:17:27 - Is Your Harness the New IDE?
00:20:18 - Why Everyone Plateaus (and the Innovation Token)
00:22:50 - Where to Actually Spend Your Time
00:24:57 - The Unhealthy Side: "It's Free Cocaine"
00:28:00 - Is This Sustainable, or Just Subsidized?
00:30:33 - Should You Run Models Locally?
00:34:31 - Looping, Scale, and Automating Review
00:37:53 - What's Left for Engineers to Do?
00:39:13 - If You Love Writing Code, You're in Trouble
00:41:18 - Why Teams Are Getting Smaller
00:43:03 - What an "Agentic Company" Looks Like
00:46:25 - How to Start: Find Your Spark
00:50:13 - The One Habit That Keeps You Ahead

Guests:
Jeroen Gordijn: https://www.linkedin.com/in/jeroengordijn
Jeroen Dee: https://www.linkedin.com/in/jeroendee

#AgenticEngineering #SoftwareEngineering #Agents

AI generates 10x more code, but your senior engineers still review it by hand and it's burning them out. Even Google admits code review is now the bottleneck nobody knows how to solve.
Florian Buetow, AI engineer at Xebia, has been running experiments to eliminate the human from the review loop entirely, and what he found changes where engineers should focus their effort.
In this episode, we cover:
Why "stop doing code reviews" is a serious answer (and what replaces them)
The guardrails that gave the most value: Semgrep rules, architectural unit tests, and stop hooks
Why your harness matters more than the model
How Amazon and Google police AI-generated code with policies
AI burnout, cognitive debt, and "cognitive surrender": what stays your responsibility
Step one for adopting agentic software engineering in your team this week
Whether you're an individual developer drowning in AI-generated PRs or driving AI adoption across a large engineering org, you'll leave with concrete experiments to run.
More from Florian:
https://cracking-ai-engineering.com

Timestamps:
00:00:00 - Intro
00:00:40 - Code Review Is Software Engineering's Biggest Bottleneck
00:01:57 - How Amazon and Big Tech Police AI-Generated Code
00:02:55 - Horizontal vs Vertical Scaling of AI Engineering
00:04:37 - Why "No Code Reviews" Might Be the Answer
00:05:22 - Engineering Environments That Give Agents Feedback
00:06:46 - Why the Harness Matters More Than the Model
00:07:21 - When Spec-Driven Development Failed and TDD Worked
00:10:06 - Stop Hooks, Ralph Loops, and Automated Feedback
00:11:30 - The Guardrails That Gave the Most Value
00:14:00 - Architectural Constraints That Keep AI Code Sane
00:15:07 - What Remains a Human Responsibility
00:17:33 - Why All the Hard Work Moves Upfront Now
00:18:47 - The Incredible Skill Junior Engineers Should Learn
00:20:26 - AI Burnout: Why Engineers Are Exhausted
00:22:42 - Cognitive Surrender: Letting the Agent Take Over
00:23:25 - The Hand Grenade Problem with AI at Work
00:24:08 - Outsourcing Code Review to AI Itself
00:26:39 - Teams That Fully Adopted Spec-Driven Development
00:29:01 - Can You Rebuild Software From Tests Alone?
00:30:27 - How to Experiment and Stay Ahead
00:33:15 - Spying on What Subagents Tell Each Other
00:33:59 - Step One: How to Start with Guardrails
00:36:08 - Data Mining Your Session Logs for Patterns
00:37:00 - Stuck With One Harness? Here's What to Do
00:38:28 - The One Experiment to Run This Week
#softwareengineering #aicoding #codereview

Are you ready to adapt to the rapidly evolving rules of software development?
In this deep dive, Logan Kilpatrick, Director and Engineer at Google DeepMind, breaks down how AI agents, advanced model-product symbiosis, and tools like Gemini 3.5 Flash are fundamentally shifting the engineering bottleneck. Learn how to maintain your competitive advantage by moving beyond the keyboard to focus on problem-solving, architectural taste, and system understanding.
In this video, we cover:
The changing role of the IDE and the rise of agent managers in code generation.
Overcoming team bottlenecks in code review and CI/CD test execution execution loops.
Why "agent coverage" and context integration are the next big tech stack metrics.
Building a bulletproof software portfolio through permissionless open-source contributions.
The critical difference between outsourcing intelligence versus outsourcing understanding.
This episode is for software engineers, tech leads, and computer science students looking to future-proof their careers and reset their ambitions in the era of autonomous engineering agents.
Timestamps:
00:00:00 - Intro
00:00:40 - Code Review Is Software Engineering's Biggest Bottleneck
00:01:57 - How Amazon and Big Tech Police AI-Generated Code
00:02:55 - Horizontal vs Vertical Scaling of AI Engineering
00:04:37 - Why "No Code Reviews" Might Be the Answer
00:05:22 - Engineering Environments That Give Agents Feedback
00:06:46 - Why the Harness Matters More Than the Model
00:07:21 - When Spec-Driven Development Failed and TDD Worked
00:10:06 - Stop Hooks, Ralph Loops, and Automated Feedback
00:11:30 - The Guardrails That Gave the Most Value
00:14:00 - Architectural Constraints That Keep AI Code Sane
00:15:07 - What Remains a Human Responsibility
00:17:33 - Why All the Hard Work Moves Upfront Now
00:18:47 - The Incredible Skill Junior Engineers Should Learn
00:20:26 - AI Burnout: Why Engineers Are Exhausted
00:22:42 - Cognitive Surrender: Letting the Agent Take Over
00:23:25 - The Hand Grenade Problem with AI at Work
00:24:08 - Outsourcing Code Review to AI Itself
00:26:39 - Teams That Fully Adopted Spec-Driven Development
00:29:01 - Can You Rebuild Software From Tests Alone?
00:30:27 - How to Experiment and Stay Ahead
00:33:15 - Spying on What Subagents Tell Each Other
00:33:59 - Step One: How to Start with Guardrails
00:36:08 - Data Mining Your Session Logs for Patterns
00:37:00 - Stuck With One Harness? Here's What to Do
00:38:28 - The One Experiment to Run This Week
#SoftwareEngineering #AIAgents #GoogleDeepMind

As AI agents transform software engineering, how do you leverage them without losing your coding skills or risking production disasters? In this episode, Google Cloud AI Director Addy Osmani breaks down the shift from babysitting basic models to mastering advanced agent harnesses.
Discover how to safely delegate complex technical tasks while maintaining your human engineering identity and setting up secure boundaries for your AI.
In this episode, we cover:
Human Identity vs. Machine Identity: How to avoid the trap of "cognitive surrender" and keep your critical thinking sharp.
Stopping the AI "Babysitting" Cycle: How to transition from constant manual oversight to secure agent governance.
Rising Abstractions: Why agent harnesses (like Claude Code and Antigravity) are changing how software is built.
The Verification Bottleneck: Why coding is easy, but verifying that your agent didn't ruin production is the real challenge.
This episode is a must-watch for software engineers and tech leaders looking to integrate AI agents into their workflows safely and effectively. You’ll walk away with actionable frameworks to boost your development velocity without letting your own technical edge rot.

Guest:Addy Osmani is a Director at Google Cloud AI, famous for his work on Google Chrome and focused on AI agents in software engineering.

Timestamps:00:00:00 - Intro
00:00:45 - The Reality of "Babysitting" Your AI Agent Setup
00:01:16 - How to Stop Babysitting and Build Secure AI Agents
00:02:36 - The Dangerous Mistakes of Uncontrolled AI Experiments
00:03:39 - Rising Abstractions: From Code to Agent Harnesses
00:05:18 - Why You Should Delegate Technical Tasks to AI
00:07:05 - How to Choose the Best AI Agent Harness
00:08:31 - How to Manage Your Developer Innovation Budget
00:10:17 - Are We Losing Pair Programming to AI Agents?
00:12:14 - Cognitive Surrender: The Hidden Threat of Generated Code
00:13:40 - The Verification Bottleneck: How to Trust AI Code
00:15:59 - How to Safely Scale Your Personal AI Bandwidth

#AIAgents #SoftwareEngineering #DeveloperProductivity

After 250 episodes of Beyond Coding, a pattern shows up again and again: the engineers who thrive aren't the ones chasing the newest tool or the cleanest code. They're the ones who learn fast, keep things simple, and understand the business they're building for.
This special pulls the sharpest moments from recent guests into one conversation about what actually makes a great software engineer in 2026.
We cover:
Why learning is the only skill that outlives every tool, language, and platform
How the best architects act more like scouts than cartographers
Why "simple is complicated enough" beats clean code dogma at scale
How to design systems that evolve instead of trying to predict 10 years out
What junior engineers should actually do in the age of AI agents
For software engineers who want to think clearer, build better, and grow into the kind of engineer companies can't replace.

Timestamps:
00:00:00 - Intro
00:00:17 - Why You Should Increase Your Breadth, Not Just Focus
00:02:16 - The Only Skill That Survives Every Tech Cycle
00:04:14 - Buzzwords Are Just Old Ideas in New Clothes
00:05:26 - What Clients Say vs What They Actually Want
00:06:45 - The Bad Architects Are Easier to Spot
00:08:50 - Why Good Engineers Use Boring Technology
00:11:40 - Stop Building for 100x Scale on Day One
00:13:13 - The Dogma of Clean Code Is Hurting You
00:15:15 - Simple Is Complicated Enough at Scale
00:16:28 - Design Only for the Next Order of Magnitude
00:18:19 - How to Talk Tech with Non-Technical Stakeholders
00:19:30 - The $50,000-Per-Hour Container Terminal Lesson
00:22:11 - Architects Are No Longer Cartographers, They're Scouts
00:25:18 - Start with a Question, Not an Answer
00:26:49 - Junior to Senior in the Age of AI Agents
00:27:29 - Don't Be a Fool with a Tool
00:29:43 - From Explicit to Implicit Knowledge Economy
00:30:38 - Use AI to Validate, Not to Generate

#softwareengineering #engineeringcareer #softwarearchitecture