{"slug":"servetia-gives-the-spanish-prime-minister-s-office-an-ai-research-platform-with-source-referenced-answers-and-local-open-weight-models","url":"https://findausecase.com/use-cases/servetia-gives-the-spanish-prime-minister-s-office-an-ai-research-platform-with-source-referenced-answers-and-local-open-weight-models","title":"ServetIA gives the Spanish Prime Minister's Office an AI research platform with source-referenced answers and local open-weight models","description":"ServetIA is an LLM-based research platform built within the PresidencIA programme for advisors in the Spanish Prime Minister's Office. Staff pose policy questions and receive structured, source-referenced responses, with a deep research module and verified citations. For sensitive use cases it can use open-weight models running on local infrastructure instead of the cloud. The platform is in beta and in active use by PM Office staff; the source gives expected impacts, not measured results.","company":"Spanish Prime Minister's Office","industry":"Government & Public Sector","country":"Spain","aiCapabilities":["Generative AI"],"deployment":"Unknown","problemStatement":"Government advisors in the Prime Minister's Office routinely research complex policy topics, prepare briefing documents and synthesise information from multiple sources under tight deadlines. Traditional methods are slow and resource intensive, and off-the-shelf AI tools raise concerns about data privacy, accuracy and suitability for sensitive government contexts.","solutionApproach":"ServetIA is a custom-built research platform within the PresidencIA programme, built on large language model technology. Staff can pose policy questions and receive structured, source-referenced responses, conduct literature review and generate drafts with verified citations, and a deep research module handles multi-source investigations. The platform prioritises grounding, using retrieval-augmented generation first and Agentic Grepping later together with source citation features. It uses both cloud-based and on-premises models; for sensitive use cases it can use open-weight models on local infrastructure instead of the cloud.","businessValue":"The platform is in beta and in active use by PM Office staff for research and analysis. The source says early use shows the tool helps staff quickly identify relevant sources and synthesise policy backgrounds. Reduced briefing preparation time and improved source citation quality are described as expected impacts, not measured results.","evidence":{"band":"high"},"sourceUrl":"https://oecd.ai/en/dashboards/policy-initiatives/servetia-ai-research-platform-for-the-spanish-prime-ministers-office","dates":{"publishedAt":"2026-10-16T05:47:13.997Z","publishedAtSource":"pipeline","updatedAt":"2026-10-16T05:47:13.997Z"},"license":"Open for reading and citing with a link to https://findausecase.com/use-cases/servetia-gives-the-spanish-prime-minister-s-office-an-ai-research-platform-with-source-referenced-answers-and-local-open-weight-models. Bulk republication requires permission."}