Index / Writing

Notes on building things.

Business, startups, product, software architecture and applied AI. 105 posts. Subscribe via RSS.

Series

13
Startup Basics · 14 partsStart: Default Alive or Default Dead? Runway Math for Small Startups
  1. Default Alive or Default Dead? Runway Math for Small Startups
  2. Your First 10 Customers Won't Come From Marketing
  3. Unit Economics in Plain English: CAC, LTV, Payback and Margin
  4. Validate an Idea in One Week
  5. Product-Market Fit: How to Know You Have It
  6. Cohort Retention: The Chart That Tells the Truth
  7. How to Price a SaaS or API: Value Metrics, Tiers and Trials
  8. Positioning: Who It's For and Why It's Better
  9. Distribution Beats Product
  10. Activation: The First Five Minutes
  11. Founder-Led Sales
  12. Pivot or Persevere
  13. Cap Tables in Plain English: Who Owns What, Round by Round
  14. Your First Hire: When, Who, and What It Really Costs
Hosting, by the Numbers · 5 partsStart: A 10-Unit Host's Morning, Before and After Automation
  1. A 10-Unit Host's Morning, Before and After Automation
  2. Automate Your Guest Messages Without Sounding Like a Robot
  3. The Real Math of One Airbnb Unit: Where Every $100 Goes
  4. Do You Need a Channel Manager at 1–10 Listings?
  5. Airbnb Market Prices, Done Right: Real Data Without Scraping
AI Engineering · 5 partsStart: Build an MCP Server: Give Your AI Agent New Tools
  1. Build an MCP Server: Give Your AI Agent New Tools
  2. How to Evaluate an AI Feature: Build Your First Eval Set
  3. RAG From Scratch: Let AI Answer From Your Own Documents
  4. Run AI Models on Your Own Laptop: A Practical Guide
  5. How to Read an ML Paper in One Hour
RIAI Lab Notes · 6 partsStart: RIAI: Toward a Terminal Agent That Writes Its Own Skills
  1. RIAI: Toward a Terminal Agent That Writes Its Own Skills
  2. A Terminal That Learns What Commands Do
  3. Writing Its Own Code: From a Teacher Model to Code Built by Search
  4. Next: Teaching an Agent to Imagine Code With JEPA
  5. Watching JEPA Write Code Live: What It Got Right, and the Check It Fooled
  6. What the Research Says: Mapping RIAI Against the Field
How AI Works · 5 partsStart: How ChatGPT Actually Works, Explained Simply
  1. How ChatGPT Actually Works, Explained Simply
  2. What's a Token, and Why AI Has Limits
  3. How AI Turns Words Into Numbers: Embeddings Explained
  4. How AI Knows What "It" Means: Attention Explained
  5. Inside a Transformer: One Word's Journey to the Next Word
Business Essays · 6 partsStart: People Don't Pay for Features. They Pay to Do Less.
  1. People Don't Pay for Features. They Pay to Do Less.
  2. Your Real Competitor Is a Spreadsheet
  3. Boring Businesses Make the Best Businesses
  4. AI Won't Replace Small Business Owners. It Will Replace Their Busywork.
  5. Investors or Independence? When a Small Startup Should Raise
  6. Why Most Small Service Businesses Charge Too Little
Applied AI · 12 partsStart: The Rise of Generative AI: Simplifying Learning
  1. The Rise of Generative AI: Simplifying Learning
  2. Generative AI Large Language Model – Train From Pre-trained Model
  3. Recommendation System: How Important Is It?
  4. How to Tell If an AI Product Is Real or Just a Demo
  5. The Hidden Costs of AI Tools Nobody Shows in the Demo
  6. What an "AI Agent" Actually Is, Without the Hype
  7. Why Santara Sends One Briefing, Not a Chatbot
  8. Stop Getting Generic Answers From AI: The 5-Part Prompt Recipe
  9. 5 Famous AI Demos That Weren't What They Looked Like
  10. Using AI With Customer Data: The Traffic Light Rule
  11. "Built With AI in a Weekend": What Happened Next
  12. A Chatbot Sold a Car for $1: 5 AI Fails Every Business Should Know
After Vibe Coding · 9 partsStart: Vibe Coding Is Real. So Is the Bill.
  1. Vibe Coding Is Real. So Is the Bill.
  2. You Can't Fix What You Can't Read
  3. Debugging When the AI Is Out of Ideas
  4. The Security Holes AI Writes Every Day
  5. Data Outlives Code
  6. Tests Are How You Talk to the AI
  7. From Prompting to Architecture
  8. Shipping Is Half the Job
  9. The Junior Developer's Roadmap for 2027
The One Sheet · 4 partsStart: The One Google Sheet That Runs a Small Business
  1. The One Google Sheet That Runs a Small Business
  2. Your Spreadsheet Keeps Beating Every App You Try. Here's When to Switch.
  3. An Airbnb Cleaning Schedule in Google Sheets That Builds Itself From Check-outs
  4. Know Who Owes You: An Invoice and Payment Sheet for Small Businesses
The Road to AGI · 8 partsStart: What Does "AGI" Even Mean?
  1. What Does "AGI" Even Mean?
  2. Bet #1: Write Down the Rules (Symbolic AI)
  3. Bet #2: Let It Learn (Neural Networks)
  4. Bet #3: Reward Is Enough (Reinforcement Learning)
  5. Bet #4: Just Make It Bigger (Scale)
  6. Bet #5: Teach It to Think (Reasoning and Agents)
  7. The Other Bets: Neurosymbolic, World Models, Brains and Evolution
  8. AGI: Where We Are Now (October 2026)
How AI Works: Advanced · 12 partsStart: Interpretability: How Scientists Look Inside an AI's Mind
  1. Interpretability: How Scientists Look Inside an AI's Mind
  2. Mixture of Experts: Why Giant Models Only Use Part of Their Brain
  3. Long Context and the KV Cache: How AI Reads a Whole Book at Once
  4. Shrinking AI: Quantization and Distillation Explained
  5. Why AI Runs on GPUs
  6. How AI Sees: Vision Transformers and CLIP
  7. How Image Generators Work: Diffusion Explained
  8. Glitch Tokens: The Strange Words That Broke GPT-3
  9. Reward Hacking: When AI Wins the Wrong Game
  10. AI Benchmarks and Goodhart's Law: Why Leaderboards Mislead
  11. Synthetic Data and Model Collapse
  12. World Models: Can AI Simulate Reality?
Founder Lessons · 6 partsStart: My First Business Teacher: William Christopher Skelley
  1. My First Business Teacher: William Christopher Skelley
  2. Read Every Word You Sign: Term Sheets for First-Time Founders
  3. What Steve Jobs Teaches Founders, the Light and the Dark
  4. Nothing Was Wrong. That Was the Problem.
  5. Choosing a Co-Founder: What I Checked Before Saying Yes
  6. Strangers Trading With Strangers: What Chợ Gem Taught Me About Trust
Software Design · 8 partsStart: Clean Architecture in Practice: How to Structure Large Backend Systems
  1. Clean Architecture in Practice: How to Structure Large Backend Systems
  2. Writing Better Code with SOLID Principles
  3. Background Jobs Done Right: Queues, Retries and the Outbox Pattern
  4. Multi-Tenant SaaS Database Design: Tenant IDs, Isolation and Row-Level Security
  5. Start With a Modular Monolith, Not Microservices
  6. Time, Money and IDs: The Data Types That Bite Backend Developers
  7. Treat the LLM Like an Unreliable API: Designing AI Pipelines That Hold Up
  8. Integrating Airbnb, Booking.com and WhatsApp: Lessons From Messy APIs

Latest

1–12 of 105