The Archive · 2013 — Now
AI archive.
137 posts in this category
137 essays in the archive · 13 languages · 45 categories
How I Write System Prompts That Actually Get Enforced (After My AI Hosts Said 'Trời ơi' 13 Times)
I spent days crafting a system prompt for my AI podcast hosts. They read every word and ignored almost all of it. The fix wasn't better words — it was understanding that LLMs process rules differently depending on where they live in your pipeline.
Read the analysis
AI-native agency vs traditional agency
An AI-native agency and a traditional agency are not the same business with a bigger tool budget. The difference is where the default sits, how the work is staffed, and what the client is actually buying. Traditional sells a team and its hours; AI-native sells an operating model and judgement, with the machine doing the first pass.

What stays in-house vs agency in the AI era
In the AI era the in-house-versus-agency decision is no longer mainly about cost. Keep the layers that compound — brand judgement, first-party data, and the client memory that makes AI improve — and use agencies for elastic production and specialist execution. The deciding question moved from price to compounding.
The Full Index
Earlier entries
Sort: Newest
The One Question That Killed an Entire Curriculum Architecture in a Week
No. 05AIHow many people does an AI-native agency need?
No. 06AIHow to price AI agency services
No. 07AIOffline Mode for My AI App Didn't Need AI. It Needed Boring.
No. 08AIIs an AI-native agency cheaper than a traditional one?
No. 09AINative Isn't a Skin: Rebuilding DIALØGUE's iOS App
No. 10AIWhat should an agency stop selling in the AI era?
No. 11AII Rebuilt My Site With Two AI Models: Opus for Design, Codex for Execution
No. 12AIHow to start an AI-native agency
Subscribe
Get the next useful note when there is something to say
I write about AI, work, expat life, and building products. Pick the topics you care about, and I'll send the next one when it's worth your time.
