Writing
Notes on putting AI into production.
What I've learned shipping AI for real clients. Short, practical, and written by me.
- 23 October 2026
RAG vs fine-tuning vs long context: which one does your product need?
Three ways to make a language model know your stuff, in plain terms. When each one fits, what each costs, and the order I try them in on real projects.4 min - 23 October 2026
MCP explained for business teams: connecting AI to your own tools
What the Model Context Protocol is, why Claude, ChatGPT and Cursor all support it, and how to give AI access to your internal systems without losing sleep.3 min - 23 October 2026
How to test an LLM feature before it reaches your customers
A plain guide to evals: the small set of real examples that tells you whether an AI feature works, and keeps it working every time you change something.3 min - 23 October 2026
Hiring an AI engineer in India: time zones, rates and how to vet one
What it's really like to hire an AI engineer from India: how the time zones work, what rates look like, and the questions that separate builders from tinkerers.4 min - 23 October 2026
Freelancer, agency or forward deployed engineer: who should build your AI project?
An honest comparison of the three ways to get an AI project built: what each costs, how each works with your team, and which one fits which kind of project.3 min - 23 October 2026
How much does it cost to build an AI agent?
Most AI agents I build cost $8k to $30k to get one workflow into production. Here's where the money goes, what pushes it up, and what it costs to run after.4 min - 19 October 2026
Why most AI pilots stall before production
The model is rarely the problem. Here's where AI projects actually get stuck between the demo and real users, and what to do about each one.2 min - 12 October 2026
What a forward deployed engineer actually does
Forward deployed engineering explained by someone who's done it for over a decade: what the role is, how it differs from consulting, and when you need one.2 min