Search
10 chapters, 63 sections, searched in the browser
This runs against a small index built from the chapter files, entirely on your machine. No server, no external service, nothing sent anywhere. With JavaScript off you get the full list below instead, which is a reasonable way to search a corpus this size too.
All 10 chapters
- 01
Context Engineering
How do you give an AI agent the context it actually needs?
- What is context engineering, and how is it different from prompting?
- How do you structure the first phase of a build?
- How do you hand the context over when the build starts?
- What belongs in an agent’s context, and what does not?
- Why does an agent drift, and where does it start?
- How do you carry context across sessions and across agents?
- Does any of this change if you cannot read the code?
- 02
Agent Memory and Second Brains
How do you give an AI agent memory that survives the session?
- Why does an agent forget, and why is that hard to fix?
- What kinds of memory are there, and which one do you actually need?
- What is a second brain, in concrete terms?
- How does the model actually reach the notes?
- What changes once your thinking outlives the session?
- What happens when more than one person contributes?
- What went wrong building this?
- 03
Coding Agents and Harnesses
What is the difference between a model and the harness you run it in?
- What does a coding harness actually do?
- What is a harness made of?
- Does the model or the harness decide the outcome?
- How do the harnesses I have used actually compare?
- How much should you let an agent do on its own?
- How do you avoid betting on a tool that changes under you?
- Does a harness actually save its state when you tell it to?
- 04
Building Without Being a Developer
Can you ship production software without being able to write the code?
- 05
Orchestration and Multi-Agent Work
When is more than one agent worth the trouble?
- 06
AI Sovereignty and Open Weights
What does it mean for a European organisation to control its own AI?
- 07
Organisational Design for the AI Era
How should a company reorganise itself around AI, if at all?
- 08
Verification
How do you know an agent's work was right if you did not watch it happen?
- 09
What I Shipped and What It Cost
What have you actually built, and what did it take?
- 10
Every Product Needs a Home
How should a product's website be built now that agents are both the builders and the readers?
- Why does a product still need a website when anyone can build an app?
- What does “static” mean now, and why is it the secure default?
- Who is the site for, if Google stopped being the sales channel?
- What does integrated conversation look like, as opposed to a chat widget?
- What does it cost, and where does it run?
- How do you brief a coding agent to build one?