Volume 1 — The Informational/Epistemic Layer
How models think, how meaning is steered, and how state becomes usable.
Reports
AI-ENG-A — Model Steering: Harness Engineering, Prompt Semantics & Adaptation Choice
Moves beyond prompt engineering into systematic model steering. Covers prompt structure, harness design, instruction hierarchy, latent-space shaping, task framing, output contracts, and the strategic choice between prompting, RAG, memory, fine-tuning, distillation, and tool use. Teaches when each method is powerful, brittle, excessive, or simply the wrong tool.
AI-ENG-B — Context Architecture: State Management & The Tenure Principle
Treats context as a managed state layer rather than a bag of semantically similar text. Covers session state, cross-session memory, belief-state design, hard scope isolation, named entity resolution, bounded vocabularies, temporal validity, “why it matters” fields, fact-to-instruction conversion, and the prevention of stale or contradictory memory contamination.
AI-ENG-C — The Economic Physics of Inference: Tradeoffs, Cost Attribution & System Margins
Defines the physical and financial laws of AI systems. Covers the tradeoffs among latency, quality, reliability, cost, throughput, context size, model class, and infrastructure. Shifts cost thinking from “model price” to granular attribution by feature, workflow, tenant, user journey, and business outcome.