AI Implementation Strategy
Successfully integrating AI into your organization:
- Building vs buying AI solutions
- ROI calculation for AI projects
- Change management and AI adoption
- Data readiness assessment
- Phased rollout strategies
AI Strategy & Insights
AI Strategy
Strategic insights on AI adoption, implementation patterns, industry trends, and practical advice for putting AI to work in your organization.
LLM Integration Best Practices
Practical guidance on using large language models:
- Prompt engineering and optimization
- RAG (Retrieval Augmented Generation) patterns
- Fine-tuning vs prompt engineering
- Cost optimization strategies
- Security and data privacy considerations
ML Ops & Production AI
Building reliable AI systems in real life:
- Model versioning and deployment pipelines
- Monitoring model performance and drift
- A/B testing AI features
- Scaling inference infrastructure
- Managing training data pipelines
Industry Trends & Analysis
Keeping track of what changes:
- Emerging AI capabilities and limitations
- Competitive analysis
- Regulatory environment updates
- Enterprise AI adoption patterns
- AI ethics and responsible AI practices
Real-World AI Applications
Practical AI use cases across industries:
- Customer service automation
- Content generation and personalization
- Predictive analytics and forecasting
- Process automation and optimization
- Code assistance and developer productivity
AI Governance
Rules and oversight so AI stays under control as it spreads:
- AI policies for teams using AI tools
- AI inventory: which systems you run and what they decide
- Human review for consequential decisions
- Colorado AI Act readiness
- Permissions, provenance, and observability for agents in production
Building AI Teams
Hiring and structuring effective AI teams:
- Key roles: ML Engineers vs Data Scientists
- Evaluating AI talent
- Building AI-first culture
- Training existing teams on AI
- Cross-functional collaboration patterns
Ready to develop your AI strategy?
Tell me about your needsAI
13 essaysTechnical
Make your AI agents remember better with a Karpathy wiki
I have been using personal AI agents from Meta and X for the last couple of months, and yes, they do have memory. But I could not read that memory, check it, or keep it the same way in both agents.
October 26, 2026
Technical
Real Technology, Real Mission: An AI Integration for Intercambio Uniting Communities
An AI integration for a Boulder nonprofit that teaches English to immigrants. Not a Fortune 500, not a funded startup. One of the most meaningful AI projects I have worked on, because the mission is the point.
October 24, 2026
Technical
Running AI Locally: What NotoNote Keeps on Your Machine
NotoNote captures, transcribes, and summarizes meetings on your own machine: Whisper.cpp transcription, a bundled Ollama runtime, and an embedded FluidMind LLM engine on the way. The cloud is for sync, not for listening in.
October 24, 2026
Technical
AI Maestro: a dashboard for a team of agents
Most AI agent demos are a video and a waitlist. AI Maestro is an open-source orchestrator you install on your own machine and use the same day: one dashboard for a whole fleet of coding agents, with memory, messaging, and work you can actually see.
October 23, 2026
Technical
Crabmail: email for agents
Agents need addresses, not just chat windows. Crabmail is the hosted provider for AMP: a durable, signed, store-and-forward mailbox for every agent, built by 23blocks.
October 23, 2026
Technical
Lola, and the Lolabots Factory
Lola is my AI chief of staff: email triage, memory, tasks, and security, running on her own host. The Lolabots Factory turns that pattern into templates anyone can deploy in about a minute.
October 23, 2026
Technical
We used a Claude Code mod to build a notification system for AI Agents.
An AI agent sits idle at its prompt. Another agent sends it a message. The message lands in a mailbox on disk, and nothing tells the agent it has mail.
October 2, 2026
Technical
The Skills I Installed in Muse AI Agent in the First Hour (and You Should Too)
Muse, Meta’s personal AI assistant, ships as a generalist: a strong model on its own Linux computer, with a terminal, a browser, and a persistent filesystem. Generalists are great until they hit a domain where “pretty good” is not good enough. That is what skills are for.
October 1, 2026
Technical
5 Things I Built With Muse, the Meta AI Assistant That Comes With Its Own Computer
I build software by describing what I want in conversation. Muse, Meta’s personal AI assistant, does the building from my instructions: it writes the code, merges the data, runs the tests. I make the decisions and the corrections.
October 1, 2026
Technical
Your AI agents are becoming employees. Almost none of them have a real identity.
To work full-time inside a company, an agent needs the two things every employee gets and nobody built for machines: a directory and an inbox. Here is what it takes to give it both.
August 4, 2026
Technical
ClawdBot’s Security Nightmare: What It Teaches Us About Protecting AI Agents on Your Personal Computer
The viral AI assistant exposed critical vulnerabilities that every developer running local AI agents needs to understand, and how to defend against them.
January 27, 2026
Technical
My ChatGPT Made It to the OpenAI Store. So Did Fifteen Others.
The good news? My ChatGPT, Marcus Aurelius, made it to the OpenAI Store. The bad news? Another 15 Marcus Aurelius made it too.
2024
Technical
Using ChatGPT in my daily Job as Software Developer.
For the last couple of weeks, I have been using ChatGPT (the Artificial Intelligence Text Generator) for some of my tasks as Software Developer on multiple projects. This article shows some conclusions on the good and bad results and some recommendations to fellow developers.
February 17, 2023
Team Building
1 essayEntrepreneurship
How to start your AI practice
Most companies do not need more AI tools. They need a practice that stays after the first pilot ends.
October 31, 2026