Index / Writing / Page 2
Notes on building things.
Business, startups, product, software architecture and applied AI. 105 posts. Subscribe via RSS.
Page 2
13–24 of 105What Actually Happens When You Open a Web Page
Type a URL, press Enter: DNS, TCP, TLS, HTTP/2 and HTTP/3, a CDN edge and the browser's rendering path, traced with real dig and curl output.

Unit Economics in Plain English: CAC, LTV, Payback and Margin
What one customer costs, earns and keeps for you. CAC, LTV, payback and margin explained simply, with three worked examples and a Python sheet.

Your First 10 Customers Won't Come From Marketing
At zero, ads and SEO have nothing to amplify. Where first customers really come from, how to talk to them, and a 4-week plan to go from 0 to 10.

Default Alive or Default Dead? Runway Math for Small Startups
Paul Graham's one-question test for startups, made practical: burn, runway, break-even, a worked SaaS example and a 15-minute monthly check.

Airbnb Market Prices, Done Right: Real Data Without Scraping
Why a scraper bot for Airbnb prices is the wrong tool, the legitimate sources hosts and developers can use instead, and a worked example with real Bangkok data.

How to Read an ML Paper in One Hour
A three-pass method for reading machine learning papers in an hour: what to read, what to skip, and how to check the experiments before you trust a claim.

Run AI Models on Your Own Laptop: A Practical Guide
How to run open AI models locally: the memory arithmetic, picking a size for your machine, GGUF and MLX, Ollama, llama.cpp, LM Studio, and Python.

RAG From Scratch: Let AI Answer From Your Own Documents
Build retrieval-augmented generation step by step in Python: chunking, local embeddings, search, hybrid BM25, re-ranking, cited prompts and evals.

How to Evaluate an AI Feature: Build Your First Eval Set
A practical guide to evals for AI features: build a case set from real usage, pick graders, read the statistics honestly, and gate changes in CI.

Build an MCP Server: Give Your AI Agent New Tools
What the Model Context Protocol is, how hosts, clients and servers fit together, and how to build, test and secure a small MCP server in Python.

The Math Behind AI, Learned From What You Already Build
Six areas of math explain almost everything in modern AI. Plain English, one runnable numpy example each, and a 12-week path for developers.

What the Research Says: Mapping RIAI Against the Field
RIAI Lab Notes #6: I read four research fields against my own results. What others built, where RIAI stands, and the experiments I'll run next.
