Sources

Reference library

Primary papers, specifications, documentation, and durable books used to ground the fieldbook. Links favor original sources and maintained standards.

Models & learning

• Vaswani et al., Attention Is All You Need
• Brown et al., Language Models are Few-Shot Learners
• Ouyang et al., Training language models to follow instructions with human feedback

Retrieval & ranking

• Manning, Raghavan, and Schütze, Introduction to Information Retrieval
• Karpukhin et al., Dense Passage Retrieval for Open-Domain Question Answering
• Lewis et al., Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks

Evaluation & measurement

• NIST, AI Risk Management Framework
• Stanford CRFM, HELM
• Liang et al., Holistic Evaluation of Language Models

Systems & reliability

• Beyer et al., Site Reliability Engineering
• Kleppmann, Designing Data-Intensive Applications
• Nygard, Release It!, second edition

Security & operations

• OWASP, Top 10 for Large Language Model Applications
• MITRE, ATLAS
• OpenTelemetry, Documentation

Source policy

Claims should point to primary material when practical. Time-sensitive operational guidance is dated. Notes distinguish measured behavior from hypotheses. Links are reviewed during major revisions, and important references are captured by title and author so they remain discoverable if URLs move.