IDEAS home Printed from https://ideas.repec.org/p/bca/bocawp/25-35.html

Money Talks: AI Agents for Cash Management in Payment Systems

Author

Listed:
  • Iñaki Aldasoro
  • Ajit Desai

Abstract

Using prompt-based experiments with ChatGPT’s reasoning model, we evaluate whether a generative artificial intelligence (AI) agent can perform high-level intraday liquidity management in a wholesale payment system. We simulate payment scenarios with liquidity shocks and competing priorities to test the agent’s ability to maintain precautionary liquidity buffers, dynamically prioritize payments under tight constraints, and optimize the trade-off between settlement speed and liquidity usage. Our results show that even without domain-specific training, the AI agent closely replicates key prudential cash-management practices, issuing calibrated recommendations that preserve liquidity while minimizing delays. These findings suggest that routine cash-management tasks could be automated using general-purpose large language models, potentially reducing operational costs and improving intraday liquidity efficiency. We conclude with a discussion of the regulatory and policy safeguards that central banks and supervisors may need to consider in an era of AI-driven payment operations.

Suggested Citation

  • Iñaki Aldasoro & Ajit Desai, 2025. "Money Talks: AI Agents for Cash Management in Payment Systems," Staff Working Papers 25-35, Bank of Canada.
    • Handle: RePEc:bca:bocawp:25-35
    DOI: 10.34989/swp-2025-35
    as

    Download full text from publisher

    File URL: https://doi.org/10.34989/swp-2025-35
    File Function: Abstract
    Download Restriction: no
    File URL: https://www.bankofcanada.ca/wp-content/uploads/2025/11/swp2025-35.pdf
    File Function: Full text
    Download Restriction: no
    File URL: https://libkey.io/10.34989/swp-2025-35?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    References listed on IDEAS

    as
    1. Bech, Morten L. & Garratt, Rod, 2003. "The intraday liquidity management game," Journal of Economic Theory, Elsevier, vol. 109(2), pages 198-219, April.
    2. Galbiati, Marco & Soramäki, Kimmo, 2011. "An agent-based model of payment systems," Journal of Economic Dynamics and Control, Elsevier, vol. 35(6), pages 859-875, June.
    3. Pascal Bornet & Jochen Wirtz, 2025. "Agentic Artificial Intelligence:Harnessing AI Agents to Reinvent Business, Work, and Life," World Scientific Books, World Scientific Publishing Co. Pte. Ltd., number 14380.
    4. Anton Korinek, 2025. "AI Agents for Economic Research," NBER Working Papers 34202, National Bureau of Economic Research, Inc.
    5. Francisco Rivadeneyra & Nellie Zhang, 2022. "Payment Coordination and Liquidity Efficiency in the New Canadian Wholesale Payments System," Discussion Papers 2022-3, Bank of Canada.
    6. Anton Korinek, 2023. "Generative AI for Economic Research: Use Cases and Implications for Economists," Journal of Economic Literature, American Economic Association, vol. 61(4), pages 1281-1317, December.
    7. Ajit Desai & Zhentong Lu & Hiru Rodrigo & Jacob Sharples & Phoebe Tian & Nellie Zhang, 2023. "From LVTS to Lynx: Quantitative Assessment of Payment System Transition," Staff Working Papers 23-24, Bank of Canada.
    8. John J. Horton & Apostolos Filippas & Benjamin S. Manning, 2023. "Large Language Models as Simulated Economic Agents: What Can We Learn from Homo Silicus?," NBER Working Papers 31122, National Bureau of Economic Research, Inc.
    9. John J. Horton & Apostolos Filippas & Benjamin S. Manning, 2023. "Large Language Models as Simulated Economic Agents: What Can We Learn from Homo Silicus?," Papers 2301.07543, arXiv.org, revised Feb 2026.
    10. Desai, Ajit & Lu, Zhentong & Rodrigo, Hiru & Sharples, Jacob & Tian, Phoebe & Zhang, Nellie, 2023. "From LVTS to Lynx: Quantitative assessment of payment system transition in Canada," Journal of Payments Strategy & Systems, Henry Stewart Publications, vol. 17(3), pages 291-314, September.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Douglas K.G. Araujo & Harald Uhlig, 2026. "How does AI distribute the pie? Large Language Models and the Ultimatum Game," Working Papers 2026-29, Becker Friedman Institute for Research In Economics.
    2. Jeffrey Allen & Max S. Hatfield, 2025. "Can LLMs Improve Sanctions Screening in the Financial System? Evidence from a Fuzzy Matching Assessment," Finance and Economics Discussion Series 2025-092, Board of Governors of the Federal Reserve System (U.S.).

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Iñaki Aldasoro & Ajit Desai, 2025. "AI agents for cash management in payment systems," BIS Working Papers 1310, Bank for International Settlements.
    2. Nikoleta Anesti & Edward Hill & Andreas Joseph, 2025. "Inflation Attitudes of Large Language Models," Papers 2512.14306, arXiv.org.
    3. Shumiao Ouyang & Hayong Yun & Xingjian Zheng, 2024. "AI as Decision-Maker: Ethics and Risk Preferences of LLMs," Papers 2406.01168, arXiv.org, revised Jun 2025.
    4. repec:osf:osfxxx:r3qng_v1 is not listed on IDEAS
    5. Paola Cillo & Gaia Rubera, 2025. "Generative AI in innovation and marketing processes: A roadmap of research opportunities," Journal of the Academy of Marketing Science, Springer, vol. 53(3), pages 684-701, May.
    6. Ajit Desai & Jacob Sharples & Anneke Kosse, 2024. "Finding a needle in a haystack: a machine learning framework for anomaly detection in payment systems," IFC Bulletins chapters, in: Bank for International Settlements (ed.), Granular data: new horizons and challenges, volume 61, Bank for International Settlements.
    7. Samuel Chang & Andrew Kennedy & Aaron Leonard & John A. List, 2024. "12 Best Practices for Leveraging Generative AI in Experimental Research," NBER Working Papers 33025, National Bureau of Economic Research, Inc.
    8. Filippo Gusella & Eugenio Vicario, 2025. "Generative Agents and Expectations: Do LLMs Align with Heterogeneous Agent Models?," Working Papers - Economics wp2025_18.rdf, Universita' degli Studi di Firenze, Dipartimento di Scienze per l'Economia e l'Impresa.
    9. Cova, Joshua & Schmitz, Luuk, 2024. "A primer for the use of classifier and generative large language models in social science research," OSF Preprints r3qng, Center for Open Science.
    10. Irving Fisher Committee, 2024. "Granular data: new horizons and challenges," IFC Bulletins, Bank for International Settlements, number 61.
    11. Zareh Asatryan & Carlo Birkholz & Friedrich Heinemann, 2025. "Evidence-based policy or beauty contest? An LLM-based meta-analysis of EU cohesion policy evaluations," International Tax and Public Finance, Springer;International Institute of Public Finance, vol. 32(2), pages 625-655, April.
    12. Filippo Gusella & Eugenio Vicario, 2025. "Generative Agents and Expectations: Do LLMs Align with Heterogeneous Agent Models?," Papers 2511.08604, arXiv.org.
    13. Rosa-García, Alfonso, 2024. "Student Reactions to AI-Replicant Professor in an Econ101 Teaching Video," MPRA Paper 120135, University Library of Munich, Germany.
    14. Felix Chopra & Ingar Haaland, 2023. "Conducting qualitative interviews with AI," CEBI working paper series 23-06, University of Copenhagen. Department of Economics. The Center for Economic Behavior and Inequality (CEBI).
    15. Hua Li & Qifang Wang & Ye Wu, 2025. "From Mobile Media to Generative AI: The Evolutionary Logic of Computational Social Science Across Data, Methods, and Theory," Mathematics, MDPI, vol. 13(19), pages 1-17, September.
    16. Ben Weidmann & Yixian Xu & David J. Deming, 2025. "Measuring Human Leadership Skills with Artificially Intelligent Agents," Papers 2508.02966, arXiv.org.
    17. Wenjun Cao, 2025. "Black Box Absorption: LLMs Undermining Innovative Ideas," Papers 2510.20612, arXiv.org.
    18. Siting Estee Lu, 2024. "Strategic Interactions between Large Language Models-based Agents in Beauty Contests," Papers 2404.08492, arXiv.org, revised Oct 2024.
    19. Shaun Byck & Ronald Heijmans, 2020. "How much liquidity would a liquidity-saving mechanism save if a liquidity-saving mechanism could save liquidity? A simulation approach for Canada's large-value payment system Shaun Byck," Working Papers 682, DNB.
    20. Alejandro Lopez-Lira & Yuehua Tang & Mingyin Zhu, 2025. "The Memorization Problem: Can We Trust LLMs' Economic Forecasts?," Papers 2504.14765, arXiv.org, revised Dec 2025.
    21. Thomas Henning & Siddhartha M. Ojha & Ross Spoon & Jiatong Han & Colin F. Camerer, 2025. "LLM Agents Do Not Replicate Human Market Traders: Evidence From Experimental Finance," Papers 2502.15800, arXiv.org, revised Oct 2025.

    More about this item

    Keywords

    ;
    ;
    ;
    ;
    ;

    JEL classification:

    • A12 - General Economics and Teaching - - General Economics - - - Relation of Economics to Other Disciplines
    • C7 - Mathematical and Quantitative Methods - - Game Theory and Bargaining Theory
    • D83 - Microeconomics - - Information, Knowledge, and Uncertainty - - - Search; Learning; Information and Knowledge; Communication; Belief; Unawareness
    • E42 - Macroeconomics and Monetary Economics - - Money and Interest Rates - - - Monetary Sytsems; Standards; Regimes; Government and the Monetary System
    • E58 - Macroeconomics and Monetary Economics - - Monetary Policy, Central Banking, and the Supply of Money and Credit - - - Central Banks and Their Policies

    NEP fields

    This paper has been announced in the following NEP Reports:

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:bca:bocawp:25-35. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: the person in charge (email available below). General contact details of provider: https://edirc.repec.org/data/bocgvca.html .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.