Archives
A language-filtered archive view with dates, summaries, and topic cues.
A deep deconstruction of Palantir Ontology — why enterprises need a third kind of ontology, what makes it different from OWL and knowledge graphs, how it is implemented, and its costs and controversies. With two companion slide decks.
A blueprint for designing and transforming an AI-native organization—from "+AI" to "AI+", the four-layer operating system, and a one-year roadmap.
A short introduction to Coding with Agents, a complete book about building software with coding agents.
Strategy notes on budget pacing, traffic allocation, behavior decomposition, and optimization controls inside ads systems.
A technical walkthrough of ad-system architecture, candidate generation, ranking, modeling, and engineering constraints.
*Earlier in this chapter, [How Coding Agents Work](how-agents-work.md) showed you the agent loop: read context → plan → act → observe → repeat. The quality of that loop depends almost entirely on the "read context" step. Get context right, and agents produce remarkable work. Get it wrong, and no…
*In [Chapter 1](../01-prompt/README.md), you learned to communicate with coding agents — giving them context, writing clear prompts, and building persistent memory systems. Now, let's look under the hood: what actually happens when you press Enter?* *From simple autocomplete to autonomous digital…
Coding agents do not remove engineering judgment. They amplify it. The practical skill is knowing when to explore with an agent, when to turn intent into a spec, when to let the agent execute, and when to slow down for verification. The old question was whether you should "vibe code" or "spec…