17 section
Reference
The lookup shelf: every term defined, every pattern in one line, courses worth the time, a role-transition map, and the guide's single deepest chapter.
What is in here
Two lookups, one deep course, two career documents. Keep the Glossary and the Pattern Index open in a tab while you read everything else. The AI Evals Study Guide is a sixteen-chapter course in its own right and the longest thing in this repo; the Transition Guide and the course list are for planning a move rather than building a system.
01
6 min
Glossary
Every term the guide uses, defined once: ABAC and BM25 through MCP and SWE-bench Verified to zero-shot, so the chapters can stay dense.
referenceinterview
02
5 min
Pattern Index
One-line lookup for every pattern in the guide, grouped by retrieval, generation, agents, reliability, caching, security and cost, each with its tradeoff.
referencepatternsanti-patterns
03
76 min
AI Evals Study Guide
The longest chapter here: error analysis by open and axial coding, judges calibrated on a train/dev/test split, and statistical correction with judgy.
evaluationobservabilityreference
04
19 min
Role Transition Guide
Backend, QA, PM, EM and data engineers mapped onto AI roles: which existing skills transfer, which gaps to close, and which chapters close them.
careersinterviewreference
05
10 min
Courses & Learning Paths
Verified courses per topic, from Karpathy and Stanford CS324 to the DeepLearning.AI shorts and the Maven evals course, with role-based sequences through them.
referencecareers