#ai

History Repeats. Humans Forget.

Everyone is talking about AI in extremes. We said the exact same things about server virtualization and Kubernetes. Generative AI is a tool. Let's learn how to use it.

Nobody Is Going to Slow Down

The AI CEOs are calling for a slowdown. Nobody actually means it. Here is what I see when I read the pacing frontier theater.

Skin in the Game: Being Serious About AI

In 2026, sending 10,000+ engineers to in-person AI training shows real commitment. Here is what happens when teams focus on customer value over hype.

Focus on the Solution, Not the AI Hype

AI hype promises autonomous software factories and imminent AGI. In the customer trenches every day, the real work looks very different.

Open Source is Right to Reject AI Slop

Large open-source projects are shutting the door on raw AI-generated contributions. It's not out of fear. It's about survival, quality, and accountability.

The End of Coding Won't Be in 2026

Eric Schmidt says programming is ending. A programmer from 1945 would say it ended forty years ago. Both are right, and both are wrong.

Paper Tigers and Pickup Trucks

Does winning the AI tools race today actually matter? History says probably not.

Context-Driven Development: Teaching Your AI Assistant How You Think

AI coding assistants are powerful, but they're blind to your intent. Context-driven development fixes that.

Dismantling an Agentic System - Part 1

I'm a HUGE BELIEVER in people being able to leverage tools better when they understand how they work. Black boxes don't breed confidence in users. So let's do that with Agentic Development Systems.

Don't Let The Line Count Fool You. This Ain't Easy (yet)

I can't remember the last time I went a day without seeing an article about '[Google has 25% of code generated by AI](https://blog.google/technology/ai/google-gemini-next-generation-model-february-2024/)' or '[GitHub Copilot is writing 46% of code](https://github.blog/2023-06-27-the-economic-impact-of-the-ai-powered-developer-lifecycle-and-lessons-from-github-copilot/)' or '[Amazon Q has saved 4,500 developer-years](https://aws.amazon.com/q/developer/)'. The knowledge isn't in the line count. It's in how they got there.

The Vibe Coding Executive Delusion

AI tools are genuinely transforming software development. But the flood of executives claiming to ship 10,000 lines of code while running companies reveals a fundamental misunderstanding of what we're building.

2025: The Year I Learned to Wrangle AI Agents

Reflections on a year of building with Agentic AI. The good, the bad, the lazy, and why I can't go back.

The Audience Has Changed: Why We Must Stop Coding for Humans

Generative AI isn't an evolution of software development; it's a revolution. To leverage it, we must stop optimizing codebases for human eyes and start building them for Agentic verification.

When AI Can't Save You: A Senior Engineer's Crisis

Experience doesn't immunize you from confusion. A look at how GenAI can amplify your ignorance just as fast as it amplifies your productivity.

Thankful for Hope, Home, and the Agentic Future

Reflecting on security, family, and the privilege of working in Agentic AI during this pivotal moment of social change and technological breakthroughs.

It's Not the Model, It's the Context

Why upgrading to the latest frontier model won't fix your productivity if your context window is a chaotic mess.

How I Finally Deleted 60,000 Emails (And The Trick That Worked)

I had 60k+ unread emails. I'm not an Inbox Zero advocate, but I needed a reset. Here is the 'Email Bankruptcy' story, the filter trick that broke Gmail, and the AI agent I built to keep it clean.

The Forever Race: Why There Is No 'Winner' in AI

Every time a new model drops, we look for a champion. History suggests we should be looking for the victims instead.

AI Writing: From "Sounding Like Me" to "Revealing What I Know"

Why my AI writing strategy shifted from style mimicry to knowledge extraction, and how agentic workflows are the future of idea sharing.

The Four Patterns of AI Interaction in 2026

From IDE plugins to fully agentic environments, exploring the four dominant patterns for interacting with Generative AI in 2026.

Gemini CLI's Hidden Superpower: Custom System Prompts

Customize Gemini CLI behavior with custom system prompts using a simple environment variable. Tutorial + ready-made agents from Pirate to Shakespeare.

How Google's File Search API Eliminated 7 Database Tables from My RAG Pipeline

I replaced a complex RAG pipeline (GCS, Vertex AI, 7 database tables) with Google's File Search API. Same cost, 90% less code. Here's how.

Spec-Driven Development: How Our 43-Agent System Compares

How our 43-agent system implements spec-driven development. CLAUDE.md files, agent prompts, and workflow specs create predictable AI agent orchestration.

Parallel AI Agents: Cursor 2.0's 8-Agent Approach vs Sequential Orchestration

Cursor 2.0 runs 8 AI agents in parallel for better results. But does the 25-35% token cost increase justify the speed? Analysis of parallel vs sequential agents.

The 7 Agentic AI Patterns We've Been Using Without Knowing It

Analyzing formal agentic AI design patterns against our three-team agent system reveals we've been implementing these patterns implicitly across marketing, engineering, and business domains.

Google's CodeMender: When Security Tools Become Autonomous Agents

Google's CodeMender represents a fundamental shift in how we think about code security. Not just finding vulnerabilities, but autonomously fixing them. And it fits perfectly with our agent-first development approach.

Amazon's 30,000 Layoffs: Is AI Really to Blame?

Amazon just announced its largest layoffs in history while posting record profits. The narrative says AI automation is replacing jobs. The numbers tell a different story about profit maximization.

The Craftsman's Paradox

What woodworking taught me about AI coding agents and the future of software development. The Industrial Revolution didn't kill craftsmanship, and AI won't either.