How do you give an AI system your specific knowledge?
Try a live AI chatbot powered by RAG (Retrieval Augmented Generation) that knows my content. See how AI systems can be grounded with specific data to avoid hallucinations.
AI Engineer &
Cognitive Interface Researcher
14 years shipping production systems. Now on the Applied AI team at WorkOS, testing and building AI workflows daily. Here's what actually works.
Practical AI patterns that survive contact with reality
If you're building with AI and want fewer surprises, I break down the exact RAG patterns, tools, and defaults I use in production—what scales, what doesn't, and why.
This is for engineers shipping features, founders figuring out where AI actually pays off, and anyone trying to see past the demo layer.
Work or personal is fine.
Read by 4,000+ builders. No hype. Unsub anytime.
WorkOSApplied AI
PineconeRAG & Vectors
CloudflareAPIs & Edge
GruntworkAWS & IaC
Cognitive Infrastructure in Practice
Real systems I've built to transform how I work
Featured: Neurodivergent Engineering
Claude as My External Brain
How I use Claude as external executive function—autistic, ADHD, and finally supported. Biometric-aware planning, voice-to-structure workflows, and agent orchestration from mountain trails.
The insight: LLMs mirror how neurodivergent minds process—dependency graphs, verbal buffers, pattern matching. Building with this alignment unlocks sustainable productivity.
Read the full guide
Training Claude for My Brain
Systematically teaching AI to compensate for ADHD/autism patterns. Collaborative intelligence.
Read the research
Handwave: Watch + Claude Code
Voice control Claude Code sessions from your wrist. When you can't sit still, bring your AI with you.
See the project
Skills as Living Runbooks
Self-documenting processes you share with your team. Maybe bigger than MCP.
Explore the pattern
WisprFlow: 179 WPM Dev
The voice-to-text tool that unlocked untethered development. Full hands-on review.
Read the review
Biometric + AI Loop
Oura Ring data feeds Claude to prevent burnout. External signals for internal blind spots.
Learn more
In the LLM, I Saw Myself
How LLMs mirror neurodivergent cognition. Diagnosis, patterns, and building with alignment.
Learn moreDevSecCon 2025 Keynote • 32 Minutes
Ship Production Code from Mountain Trails
I traded the desk for the trail and kept shipping. Voice at 179 WPM, background AI agents, and hardened CI/CD that makes speed safe. Watch the full workflow in action.
Voice-Native Workflows
Ship production code at 179 WPM while hiking mountain trails. Voice-first development with AI transcription.
Agent-Driven CI/CD
Orchestrate background AI agents with hardened pipelines. Speed requires safety.
Untethered Development
Think where you think best. Orchestrate, don't micromanage. Ship from anywhere.
4,000+Newsletter subscribers
14 YearsShipping production systems
StaffDevRel at Pinecone
Loading visualization...
Hands-On Demos & Production Code
Don't just read about AI—interact with it. My live RAG demos, open-source projects, and battle-tested tutorials show you what actually works in production. From embeddings to fine-tuning, see the code that ships.
Try Interactive AI Demos134+ Articles & Growing
Deep dives on AI tools, voice workflows, infrastructure, and developer productivity. Real experiences from building production systems.
Let's Work Together
Have a project in mind? I'd love to hear about it. Reach out and let's discuss how I can help.
Get in TouchHow I Engage
Whether you're vetting AI investments, building production systems, or trying to understand the landscape—I can help.
📈
For Investors & Funds
Technical Due Diligence
I provide technical diligence on AI tools, stacks, and startups. Cut through the hype with hands-on analysis from a practicing engineer.
Schedule a Call
⚙️
For Engineering Teams
Fractional AI Leadership
Architect and implement production RAG, fine-tuning, and scaling strategies. Interim staff AI engineer for your startup.
Discuss a Project
📚
For Builders & Business Owners
Tools Analysis & Guides
Unbiased, hands-on reviews and tutorials (like my Wispr Flow review with 4k+ views). Learn what works to ship faster.
Browse Articles
Featured Premium Project
5.0 rating
“Thanks for publishing the tutorial, very helpful.”
Scott McCallum • Full Stack Developer at Intermine
Interactive AI Laboratory
Learn by doing! Explore how AI systems work under the hood through hands-on interactive experiences.
How do LLMs understand meaning in text?
Visualize how text transforms into vectors that capture semantic meaning. See why similar concepts cluster together and understand the foundation of RAG systems.
Why do LLMs have context limits and token costs?
See how language models break text into tokens. Understand why context windows exist, how pricing works, and optimize your prompts for better performance.
Knowledge Collections
Explore my comprehensive library of AI engineering resources and implementation guides.
Deep and Machine Learning Tutorials
Cloud GPU Services for Deep Learning and fine-tuning with Jupyter Notebooks Reviewed: Colab, Paperspace Gradient, Lightning.ai, and more
I tried a handful of services when I last needed to fine-tune an LLM, and I was mostly disappointed...
How to create a custom Alpaca instruction dataset for fine-tuning LLMs
A step by step tutorial with companion notebook.
How to Fine-tune Llama 3.1 on Lightning.ai with Torchtune
One of the better Jupyter Notebooks to GPU-backed environment experiences I've had...
Open-source AI / ML / Pipelines Projects
Building a Hand-Drawn Digit Recognizer with PyTorch and MNIST
I trained a neural net to recognize hand-drawn digits, then built a Next.js UI for it
Build a RAG pipeline for your blog with LangChain, OpenAI and Pinecone
You can chat with my writing and ask me questions I've already answered even when I'm not around
Vector Databases in Production for Busy Engineers: RAG Evaluation
I wrote the RAG evaluation chapter for Pinecone's latest book
AI-assisted Development
Autocomplete is not all you need: Why Cursor and Zed are going to dominate
AI assisted developer tooling is not created equally...
Updated Codeium analysis and review
It's been about a year since I last looked at Codeium - what has changed?
Automations - shell scripts leveraging OpenAI to make your developer workflow buttery smooth and way more fun
I have open sourced my automations project, which is a collection of shell scripts that automatically handle git operations, provide local code reviews, pull requests, and more!
Career Advice
Wash three walls with one bucket
Design your side projects, blog posts and even your fun experiments to triangulate multiple learning paths simultaneously. Then, use them to build out your portfolio.
Run your own tech blog
Control your own destiny, build your personal brand, and master web technologies by running your own tech blog.
You get to keep the neural connections
Going the extra mile only to be unrewarded by your company feels like a personal slight and a waste of your time. It is not.
Videos
How to build chat with your data using Pinecone, LangChain and OpenAI
I show step by step how to build a RAG chatbot to talk to your data in this easy to follow tutorial for beginners.
How to use ChatGPT in your terminal
Did you know you can use ChatGPT in your terminal? No more copying and pasting...
What is a vector database?
Vector databases explained, featuring clowns, embeddings, neural networks, feature extraction, semantic search and Retrieval Augmented Generation (RAG).
Reference Architectures and Demos
Testing Pinecone Serverless at Scale with the AWS Reference Architecture
A step-by-step walkthrough on how to generate arbitrary system load and flex Pinecone Serverless
Announcing the Pinecone AWS Reference Architecture in Pulumi
Deploy production-ready systems using Pinecone in minutes with the AWS Reference Architecture
Pinecone AWS Reference Architecture Technical Walkthrough
An examination of the Reference Architecture components and functionality