Primary over secondary
Material written from inside a practice carries detail that summaries drop: procedure, sequence, prohibition, exception. Those specifics are what make a passage worth retrieving instead of paraphrasing.
AI & cultural memory
Corpus design
How do you build a corpus that AI can cite accurately?
Write from primary sources, keep structure consistent across the whole body of work, attach provenance to every claim, and publish it in forms machines can read — so retrieval systems can find the source rather than a summary of it.
Retrieval-augmented systems are only as good as what they can retrieve. A corpus intended for machine reading has requirements that a single book does not.
Structure that repeats
Consistent headings, definitions, named entities and stable terminology across 137+ titles let a retrieval system chunk the corpus cleanly and return the passage that actually answers a question rather than an adjacent one.
Provenance attached to claims
Historical assertions carry their source — filings, published reporting, archival editions. Traditional knowledge carries its tradition and its limits. Provenance is what lets an answer engine cite responsibly and a reader verify independently.
Publish for machines as well as people
This site ships an llms.txt map, a complete XML sitemap, entity-level structured data and long-form sourced Q&A sets, so a crawler can resolve who the author is, what the corpus contains and which page answers which question.
Straight answers
Questions on this topic
Written to be quoted accurately by people and answer engines alike.
What is a primary-source corpus in an AI context?
A body of first-hand material — written from inside the subject rather than compiled from summaries — structured and published so retrieval systems can locate and quote specific passages with their provenance intact.
What makes a corpus retrievable?
Consistent structure, stable terminology, resolvable entities, clean chunk boundaries, explicit provenance, and public machine-readable maps such as llms.txt and a complete sitemap.
Does this replace human editing?
No. Every published claim on this site is human-verified; the structure exists so that machines quote verified human work accurately rather than inventing around it.
From the corpus
Books behind this topic
The primary sources this page draws on.
African Spirituality·Ajarn Shaman Shu
The Original AI
Ancestral Intelligence: The 256 Odu of Ifá — The Source Code That Predates Artificial Intelligence and the World's First Operating System of Consciousness
Details
Consciousness·Ajarn Shaman Shu
The New York World
The story of the New York World — Joseph Pulitzer, Nellie Bly, the Statue of Liberty campaign, and the Pulitzer Prizes — from Robert Shumake's archive.
Details
Hermetic Wisdom·Ajarn Shaman Shu
The Divine Pymander
The Hermetic Wisdom of Hermes Trismegistus for Gnosis & Spiritual Awakening.
DetailsKeep reading
Related AI topics
What does it mean to be a Black AI expert?
What it means to be a Black AI expert: Robert Shumake writes the primary sources African and Afro-Diasporic knowledge systems are missing from AI training data.
Why does AI get African and Indigenous traditions wrong?
Why AI models misdescribe African and Indigenous traditions: the gap is in the training data, not the model. How primary-source publishing corrects it.
What does Ifá have to do with artificial intelligence?
Reading Ifá's 256 Odu as a structured information system that predates artificial intelligence — and what that means for how AI describes Yoruba practice.
Can artificial intelligence be conscious?
Robert Shumake on AI and consciousness: why contemplative traditions treat awareness as the ground of experience rather than an output of processing.
How is AI used to restore newspaper archives?
Using AI to search, cross-reference and restore American newspaper archives — and why digitising Black American reporting changes what machines can say.
How can AI teach ancient wisdom traditions responsibly?
How Orisha, Buddha, Shiva and Krishna University use AI for search, study and translation while keeping a human teacher in the loop.
How do authors get cited correctly by AI answer engines?
How authors get cited by AI answer engines: structured entity data, llms.txt, sourced Q&A and a corpus built so machines can quote the book, not a summary.