Agentic AI: can we streamline economic policy briefing?
Giuseppe Bruno ()
Additional contact information
Giuseppe Bruno: Bank of Italy
No 1001, Questioni di Economia e Finanza (Occasional Papers) from Bank of Italy, Economic Research and International Relations Area
Abstract:
Central banks increasingly rely on large volumes of policy documents-ranging from monetary policy statements to regulatory guidelines and internal reports-to communicate decisions and maintain institutional accountability. These documents help ground decisions in the most up-to-date economic signals, support internal coordination and strengthen transparency toward markets and the public. Yet their complexity and frequency impose significant administrative and analytical burdens. The emergence of agentic AI, which combines large language models with autonomous goal setting, structured workflows and tool-calling capabilities, offers the potential to automate key tasks such as drafting, summarization, cross-document consistency checks, integration with data sources and the generation of tables and figures. In this paper, we address the question posed in the title by examining the role that recent advances in AI-enhanced by agent-based architectures and coordinated task execution-can play in central bank workflows. We present two simple, ground-up examples showing how open-source tools can be leveraged effectively while keeping development and operating costs under control. The paper concludes by discussing how agentic AI could reshape document processing practices within central banks, highlighting both the efficiency gains and the governance safeguards required for its trustworthy adoption.
Keywords: Language Models; LangChain; LangGraph; agent (search for similar items in EconPapers)
JEL-codes: C82 C87 O36 (search for similar items in EconPapers)
Date: 2026-03
References: View complete reference list from CitEc
Citations:
Downloads: (external link)
https://www.bancaditalia.it/pubblicazioni/qef/2026-1001/QEF_1001_26.pdf (application/pdf)
Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
HTML/Text
Persistent link: https://EconPapers.repec.org/RePEc:bdi:opques:qef_1001_26
Access Statistics for this paper
More papers in Questioni di Economia e Finanza (Occasional Papers) from Bank of Italy, Economic Research and International Relations Area Contact information at EDIRC.
Bibliographic data for series maintained by ().