How do you actually work with AI coding tools in production? From breaking down features into AI-friendly tasks? How to choose between agents vs. manual prompting? How to writing code that LLMs understand better? Where do spec-driven workflows fit in?


0:00 - Introduction
1:09 - What's the WORST thing you can do when adopting AI?
4:44 - Experimentation vs. Following Old Mental Models
7:06 - Working at Feature Level: Breaking Down AI Tasks
10:10 - Cheesy's Workflow: Brainstorming, Stride, and Task Management
13:45 - Phil's Approach: Staying in Flow State vs. Using Agents
16:01 - The Death of Prompts: Plugins and Tools Take Over
18:11 - Context Engineering vs. Prompt Engineering
21:00 - Context Window Size: Bigger Isn't Always Better
23:48 - Spec-Driven Development → Task Management Tools
25:22 - Model Wars: Anthropic vs. Open Source (Qwen, DeepSeek)
30:00 - Should You Short Anthropic Stock? (Philosophical Discussion)
33:00 - Why Claude Code Still Leads Despite Model Convergence
35:01 - Hardware Costs and the Future of AI Accessibility
38:11 - Does Boilerplate Death Change Architecture?
42:00 - When Should You Care About Code Organization with AI?
45:26 - Writing Code FOR LLMs: Semantic JavaScript and Context
47:49 - Wrap Up: Future Topics on LLM-Friendly Code

YouTube: https://bit.ly/3Xfv2bp
Apple Podcasts: https://apple.co/4bNrAJK
Spotify Podcasts: https://spoti.fi/4bZjtcA
LinkedIn Group: https://bit.ly/3wZIWDM
RSS Feed: https://bit.ly/3KsaODW
Twitter: https://bit.ly/4ecWHju

The team debates AI development workflows, introduces Stride (a multi-agent requirements system), and discusses whether programming languages and software engineering principles still matter when AI writes most of your code. They explore how product management is transforming as iteration costs plummet and MVPs now take hours instead of weeks.

• Ancillary AI Development Tools - Tools built on AI models like OpenSpec, SpecKit, and Kiro.dev that help with planning and design before coding
• Planning vs. Direct Implementation - Debate on whether extensive planning (BDD/Given-When-Then) is needed or if iterative development with AI works better
• Stride Requirements System - Cheesy's Kanban-based tool that manages multi-agent workflows, prevents merge conflicts, and matches tasks to agent capabilities
• Does Programming Language Matter? - Whether language choice still matters when AI generates code, and if developers will let AI select languages based on accuracy
• Product Management Transformation - How PM roles are shifting from managing backlogs to rapid prototyping with drastically reduced iteration costs
• Code Review and AI Trust - Evolution from reviewing every AI-generated line to relying on automated checks as confidence increases
• Software Engineering Principles - Whether core principles (DRY, SOLID, clean code) remain important - consensus is yes, they help AI work more effectively

YouTube: https://bit.ly/3Xfv2bp
Apple Podcasts: https://apple.co/4bNrAJK
Spotify Podcasts: https://spoti.fi/4bZjtcA
LinkedIn Group: https://bit.ly/3wZIWDM
RSS Feed: https://bit.ly/3KsaODW
Twitter: https://bit.ly/4ecWHju

What does the future of software development look like when AI is writing most of the code? We dive deep into how AI is fundamentally changing team dynamics, agile methodologies, and the roles we've held sacred in software engineering. We break down why humans are now the real bottleneck, how to build trust with AI-generated code, and what your development workflow should actually look like right now.

Sections & Timestamps

00:00 - Intro

0:06 - The Two Pizza Team: Still Relevant?

1:36 - Where Agile Breaks Down with AI

3:18 - Rethinking Team Structure in an AI-First World

5:06 - Can We Keep the Roles? Should We?

6:50 - From Developers to Agents: The Shift in Thinking

8:00 - Code Review is Your New Bottleneck

10:15 - The Beads Project: Never Looking at Your Own Code

12:14 - Why Companies Keep Forcing AI Into Old Processes

14:00 - Humans Are the Bottleneck Now (the Big Insight)

16:00 - How to Convince Skeptical Engineers to Trust AI Code

18:30 - Start Small, Build Confidence Over Time

21:50 - Why Brownfield Projects Are Actually AI's Sweet Spot

25:30 - Managing Context Windows and Problem Decomposition

28:00 - The Hard Problem: Testing Non-Deterministic Agents

31:50 - What We're Actually Using Right Now (Tool Rundown)

32:20 - The Rise of AI UX and Task Formatting

34:00 - Tidewave, Claude Code, and Cloud Skills

36:00 - Closing Thoughts & See You Next Time

YouTube: https://bit.ly/3Xfv2bp
Apple Podcasts: https://apple.co/4bNrAJK
Spotify Podcasts: https://spoti.fi/4bZjtcA
LinkedIn Group: https://bit.ly/3wZIWDM
RSS Feed: https://bit.ly/3KsaODW
Twitter: https://bit.ly/4ecWHju