{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T17:23:41Z","timestamp":1771867421943,"version":"3.50.1"},"posted":{"date-parts":[[2026]]},"group-title":"SSRN","reference-count":0,"publisher":"Elsevier BV","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>This study evaluated the nutritional adequacy of dog diets that were formulated by four widely used Artificial Intelligence models (Manus, ChatGPT, DeepSeek, and Gemini) in relation to the recommendations of the European Pet Food Industry Federation. Using a standardized prompt, complete and balanced diets (beef and chicken) for an 8 kg adult dog were requested. Eleven formulations were analyzed using SuperCracPet\u00ae software based on United States Department of Agriculture data. The results showed that 61.3% of the nutrients were below the minimum recommended levels. Critical inadequacies included: an energy undersupply in 81% of diets, severe calcium deficiency in 91% of formulations, drastically inadequate calcium-phosphorus ratio (0.04:1 to 0.09:1 versus ideal 1:1-2:1), complete absence of chlorine, critical vitamin deficiencies (63,7% vitamin D, 81,8% choline), linoleic acid deficiency in 72% of diets. Only 18% of the formualtions included supplementation, which was in insufficient quantity. The observed inadequacies, if implemented chronically, would cause secondary nutritional hyperparathyroidism, osteodystrophies, dermatoses, pro-inflammatory states, and progressive malnutrition. It is concluded that language models are inadequate for the autonomous formulation of canine diets because they generated prescriptions with severe flaws that compromise bone, skin, immune, and metabolic health. Safe application requires hybrid systems with mandatory supervision by animal scientists and veterinarians and also regulation to prevent avoidable risks to animal health.<\/jats:p>","DOI":"10.2139\/ssrn.6281851","type":"posted-content","created":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T16:48:52Z","timestamp":1771865332000},"source":"Crossref","is-referenced-by-count":0,"title":["Use of Artificial Intelligence in obtaining canine diets: nutritional inadequacy and the need for professional knowledge"],"prefix":"10.2139","author":[{"given":"Marco  Tulio Santos","family":"Siqueira","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9781-8396","authenticated-orcid":true,"given":"Janine","family":"Fran\u00e7a","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2222-0031","authenticated-orcid":true,"given":"Marcos  Borges Santa","family":"Rosa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6398-5033","authenticated-orcid":true,"given":"Camila","family":"Raineri","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","container-title":[],"original-title":[],"deposited":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T16:48:52Z","timestamp":1771865332000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ssrn.com\/abstract=6281851"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":0,"URL":"https:\/\/doi.org\/10.2139\/ssrn.6281851","relation":{},"subject":[],"published":{"date-parts":[[2026]]},"subtype":"preprint"}}