Coined, 2026
Corpus Engineering
Corpus Engineering is the systems-level discipline of engineering a body of content for retrieval, citation and AI generation.
"Relevance Engineering optimizes how content matches a query. Corpus Engineering optimizes the conditions that make matching possible in the first place."
AI Overviews, ChatGPT, Claude, Perplexity and Gemini reason across bodies of content, not single pages. Corpus Engineering is the discipline for that: designing, structuring, expanding, maintaining and optimizing the corpus.
Its scope has 6 parts: corpus accessibility, semantic structure, information gain, corpus expansion, retrieval optimization and corpus maintenance. The corpus is the unit of analysis, and its lifecycle is part of the work from day one.