What is sourced from primary texts, what is translated by humans, what is drafted with a language model, and what checks run before anything is published.
If you read commentary on scripture, you should know who wrote it and where a language model was involved. In short:
Every verse page and essay goes through these five steps.
Sanskrit editions in the public domain. The Bhagavad Gita text used here follows established critical editions. For the Devanagari and transliteration, we work from standard published sources, not from model output.
The English translations are the Wisdom edition, drawn from public-domain English sources. Where a specific source is identifiable, it is named. New translations going forward carry full provenance. The AI does not translate Sanskrit. It works from the human translation as its source.
Which verses are published, which are held back, and how they are organised is Ankur's call. The library the 7-day plans draw from is chosen the same way; the model only picks from inside it.
A language model drafts the commentary (simpleMeaning, detailedMeaning, modernRelevance) from the human translation and editorial context. The model gets the translation, not the Sanskrit, and is asked to explain it. Its instructions are written against the mistakes listed below.
Each piece is read against the source translation, checked for accuracy, and edited before it goes up. The review date on each page reflects the last time this check ran.
If a draft breaks any of these, it is fixed or dropped before it goes up.
Language models make up verses, misattribute commentaries, and gloss over disagreements between traditions, all in a confident tone. So verse citations, named commentators' views and cross-references are checked by hand against a sourced edition. Some mistakes still get through.
If you find a misattributed position, an invented verse, or a reading that skips over a real disagreement between schools, please tell us. Write to work.ankurshukla@gmail.com. Errors that are substantive get corrected with a visible note on the page.
The disclosure appears in three places.
A single line in the footer of every page: Wisdom translation, edited by Ankur Shukla. Commentary AI-drafted, human-reviewed. A per-post byline on each blog and verse page naming the editor, the AI-drafted commentary, and the last review date. And this page, reachable from every byline.
A model can write commentary that reads well and still reverses what a verse says, or credits it to the wrong text. Knowing a model was involved tells you to read with that in mind, and to check anything that matters to you against the Sanskrit.
Verse pages and essays carry a last reviewed date. When a substantive error is found and corrected, the date is updated and a brief note is added at the bottom of the page describing what changed.
If you find an error, please write to work.ankurshukla@gmail.com with the verse reference and the specific claim you think is wrong. Include a source if you have one. We will check it.
Wisdom is one person. Ankur Shukla builds the app, the website and the data pipeline, and does the editing. There is no separate fact-checking team, so reader corrections matter.
Report an error →