AI
AI engineering, in practice
We build software with AI agents every day and write down what works: the method, the tools and the limits.
How we work with AI
Agents do the work, people own the result
Coding agents plan changes, edit files and run the tests. A person designs the change and reviews the diff before anything ships.
Local models where they fit
Private models running on our own hardware, for work that should stay on the machine.
AI inside our products
AI features are part of the apps we're building, and of our media work. We'll show them when they launch.
Books on AI engineering
Practical guides from real work with coding agents and models. Every book has a free sample.
-
AI Engineering
Building Autonomous Coding Agents
Design, Safety, and Local-First Operation of Unattended AI Development Systems
-
AI Engineering
Agentic Coding Harnesses, Compared & Explained
Master Claude Code, Aider, OpenCode, Goose, and Codex — Then Run Them Locally
-
AI Engineering
AI-Assisted Development
Working With Coding Agents
-
AI Engineering
The Model Context Protocol (MCP) in Practice
Building, Integrating, and Scaling Custom Tool Servers for AI Agents
-
AI Engineering
Orchestrating AI Agents
Coordinating Claude Code, Codex, Local Models, and MCP with a Persistent Control Plane
-
AI Engineering
Running Local LLMs on Your Own Hardware
A Practical Guide to Private, Offline, and Self-Hosted Large Language Models
Want the full picture? Start with the books.