On AI

Humans become orchestrators

Humans will move more into an orchestration role, enabling them to 10x productivity if they use these tools effectively. AI can give us more time back to spend on the human things we love—like spending time with our families and friends. If used effectively, we can learn, build, dream, and do—faster.

Relationships remain everything

I believe relationships are today, and still will be, the single most important thing in our lives. The Harvard Grant Study—one of the longest studies of adult life ever conducted—confirms this: close relationships, more than money or fame, are what keep people happy throughout their lives. AI should serve this truth, not replace it.

We're all learning this together

AI is rapidly evolving and still "new" by any stretch. The gap between a learner and teacher is still relatively small. My best advice for anyone wanting to use AI for marketing, product, or sales: just give it a shot, learn through experimentation and collaboration, and refine your process over time. There are no shortcuts on a path that has yet to be created.

Understand what AI learned from

We still need engineers who actually know how to build things. A model trained on developer forums and public repositories is learning from a skewed dataset: roughly 50% broken code with issues, 50% solved problems. The really good stuff - working, secure, scalable, well-architected production systems - almost never exposes its source code publicly. AI is learning from the visible debris of software development, not the invisible foundations that actually work. If you don't understand what the AI learned from, you can't predict where it will fail you. The future isn't "AI replaces engineers" - it's engineers who understand both the system and the AI's blindspots becoming 10x more valuable.

Embodied context is the next frontier

Our AI is missing more than data - it's missing humanity and context from the real world. We often assume "digital context" equals full context, but internet-only data is fundamentally noisy: keyboard warriors, sarcasm, echo chambers. When AI observes not just text, but how humans act, move, and interact in physical space, it gains materially richer context. Wearables, AR glasses, robotics, and handheld devices capture motion, gesture, and environment - not just keyboard inputs.

The AI Box Model

Think about how we started - with AI in a chat window. That chat modality is "AI in the box": limited reach to external systems, trained on far more than you'd generally ask it about, constrained to simple question-and-response patterns. Then we connect the boxes - an LLM linked to a CAD system via MCP server, or a simulation engine that doesn't just answer questions but actually acts on your behalf. Finally, we move to "out of the box": AI everywhere, with connected systems and platforms generating the specific context you need. Vertical training creates specialist-level outputs versus the generalist responses you'd get from search. The biggest leap in AI isn't a bigger model - it's smarter placement of it. Think mobile phones, not mainframes.

The Antagonist agent

Traditional AI coding assistants have a fundamental flaw: they treat every interaction as isolated. The context dissolves. Rather than using a single AI agent, I orchestrate teams of specialized agents with persistent memory and adversarial quality control. The most critical innovation? The Antagonist agent - an AI specifically designed to never provide positive reinforcement. It identifies vulnerabilities, questions assumptions, and refuses to acknowledge progress until issues are genuinely resolved. This inverts the typical AI tendency toward affirmation and creates a forcing function for quality. If AI systems perform better with formalized adversarial roles, perhaps we should reconsider how we treat critical evaluation in our own processes.

Multi-agent orchestration in practice

Below is a screen capture of four Windsurf AI coding agents working simultaneously on different git worktrees for the same codebase. A fifth window (not shown) serves as the orchestration layer—directing tasks, resolving conflicts, and ensuring coherent progress across all workstreams. This isn't theory; it's how I actually build.

Four AI agents working in parallel across git worktrees, orchestrated by a fifth

Making agentic AI accessible

I've always believed that the true promise of AI is its ability to elevate our own capabilities - to make us all better. But for many, this technology remains locked behind a wall of complexity. My goal is to make agentic AI workflows accessible to everyone, regardless of technical background - teaching the principles of automation, not just a single tool.

Never copy/paste - always refine

I am strongly against copy/pasted AI output. It must be refined, nurtured, and verified. Context and data must be appropriate to ensure factually and directionally correct outputs. We must be mindful of blind spots that actually hinder us - both the AI's limitations and our own tendency to over-rely on its outputs without critical evaluation.