{"version":1,"type":"story","url":"https://digestai.news/story/ai-writes-214-page-wiki-from-45-047-enron-emails-each-fact-cited","json":"https://digestai.news/story/ai-writes-214-page-wiki-from-45-047-enron-emails-each-fact-cited.json","markdown":"https://digestai.news/story/ai-writes-214-page-wiki-from-45-047-enron-emails-each-fact-cited.md","slug":"ai-writes-214-page-wiki-from-45-047-enron-emails-each-fact-cited","headline":"AI writes 214-page wiki from 45,047 Enron emails, each fact cited","summary":"The team gave an AI 45,047 Enron emails and it produced a 214‑page wiki covering the companies, regulators and banks Enron dealt with. Every sentence includes a citation to the originating email, and facts that later became false are shown as expired on the date they changed. A second AI performed a held‑out audit to verify the pages.\n\nThe wiki groups entities into pages for organizations mentioned in at least 25 messages and for the five most‑discussed parts of Enron itself – three business units, a trading platform and a trading system. In total the system identified 209 pages with 929 entities and 5 pages with 551 entities, covering 57 narrow types, 78 products and platforms, 76 facilities and market points, and 49 events. The source data is public because the Federal Energy Regulatory Commission (FERC) released the emails during its investigation, and Carnegie Mellon has maintained the archive since 2003.\n\nThe authors argue that such a “company brain” sits beside traditional CRM systems, holding knowledge that changes too often for static fields, and they provide the prototype as a reference for anyone wanting to build similar systems.","keyPoints":["AI generated a 214‑page wiki from 45,047 Enron emails, citing each fact to its source email","Pages cover entities mentioned in at least 25 messages and five key Enron parts","The dataset is public thanks to FERC release and Carnegie Mellon maintenance since 2003"],"whyItMatters":"Demonstrates how AI can turn large email archives into searchable, time‑aware knowledge bases, reducing manual curation for companies and researchers.","category":{"slug":"agents","name":"Agents & Tools","url":"https://digestai.news/category/agents"},"entities":{"companies":["Enron","Federal Energy Regulatory Commission (FERC)","Carnegie Mellon"],"models":[],"people":["Bethany McLean","Peter Elkind"]},"firstPublishedAt":"2026-10-23T12:02:53Z","updatedAt":"2026-10-23T12:02:53Z","sourceCount":1,"hasPrimarySource":false,"sources":[{"outlet":"thisandthat.chat","title":"Show HN: We had AI write a wiki from 45k Enron emails, every fact cited","url":"https://thisandthat.chat/enron","publishedAt":"2026-10-23T12:02:53Z","type":"press","primary":false,"lead":true}],"sourceNotes":null,"discussions":[{"site":"Hacker News","url":"https://news.ycombinator.com/item?id=50207620","points":43}],"thread":null,"cite":{"text":"Digest AI, \"AI writes 214-page wiki from 45,047 Enron emails, each fact cited\", 23 October 2026, https://digestai.news/story/ai-writes-214-page-wiki-from-45-047-enron-emails-each-fact-cited","publisher":"Digest AI","title":"AI writes 214-page wiki from 45,047 Enron emails, each fact cited","datePublished":"2026-10-23T12:02:53Z","url":"https://digestai.news/story/ai-writes-214-page-wiki-from-45-047-enron-emails-each-fact-cited"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}