Agentic Intelligence: AI Methods for Bond Markets

What does it mean for an AI system to be agentic? Agentic Intelligence: AI Methods for Bond Markets answers this through modeling one of modern finance’s hardest problems: Government bond market trading. As structural pressures and regulatory concerns mount, traditional approaches fail in these complex, partially observable and bilateral trading environments.

Following unprecedented pandemic-era government debt issuance, authorities including the Reserve Bank of Australia, Bank of Canada, Bank of England, and Federal Reserve Bank of New York have prioritised enhancing the market’s liquidity and functioning. This book responds directly by building Agentic AI models – showing that Agent-Based Models (ABMs) provide the natural computational foundation for transparent market modelling, and that when LLMs are embedded with discipline, Agentic AI can uncover emergent features and behavioural realism that traditional models cannot. Dynamically adaptive and able to operate over a virtually infinite space of possibilities, Agentic AI offers a new paradigm.

The author makes three practical contributions: (1) a liquidity-centred framework that treats the ability to transact as the central systemic object; (2) Agentic AI methods that capture heterogeneous participant interaction, non-linear cost structures, and emergent liquidity; and (3) the AI-simulator testing paradigm, in which the simulator is the laboratory and the agent is the experiment – providing market participants and regulators a basis on which Agentic AI can be deployed, governed, and trusted. Readers will gain implementable methodologies for moving Agentic AI from concept to market application, supporting trustworthy AI in the trading, supervision and design of financial markets.

I have spent five decades writing about fixed income markets, and in that time the analytical toolkit has evolved considerably, but the fundamental challenge of modeling liquidity in bilateral, over-the-counter markets has remained largely unresolved. Vidler changes that. By uniting agent-based modelling with large language models into a coherent agentic AI framework, she introduces a genuinely new methodology to the field. This book is that rare work which is as valuable to the practitioner managing risk on a trading desk as it is to the researcher or regulator. It deserves wide readership.

Frank Fabozzi, Professor of Practice at Johns Hopkins Carey Business School, Author of the best-selling Handbook of Fixed Income Securities

The era of the human-only trader may be over, but human judgment has never been more vital. In “Agentic Intelligence”, Dr. Alicia Vidler expertly demonstrates that the future of financial modeling isn’t about writing more complex probabilistic equations - it’s about orchestrating virtual teams of traders, researchers, and analysts to accelerate and magnify the impact of expert human judgment and taste. By embedding Large Language Models into agent-based frameworks, Vidler tackles the world of government bonds. She proves that Agentic AI isn’t some toy for basic automation; it is a profound tool for scaling human nuance, experience, and strategic intent. Whether you are a market designer, a risk manager, or a technologist, this book is an essential blueprint for understanding how to manage the AI agents that will soon define the machinery of global liquidity.

David Rensin, Distinguished Engineer; Technical Advisor to the CFO at Google

Vidler takes off the proverbial robot mask to reveal the inner workings of complex systems in financial markets, thereby modelling in practice her argument for greater understanding of them. In a world where trust needs to be regarded as a verb, and not a noun - as a dynamic and unfolding process rather than a fixed object - Vidler offers an account of how AI systems can be trusted by drawing on cutting-edge research and her own industry experience. In doing so, she demonstrates why trust matters in volatile, time-sensitive trading conditions where rapid interpretation and response are critical.

Dr. Belinda Middleweek, Senior Lecturer, University of Technology Sydney

Dr. Alicia Vidler shows exactly why Agentic AI demands a different kind of thinking. Moving from the premise that bond markets are systemically important yet structurally opaque, she builds a compelling case for why agent-based modelling and LLMs together can illuminate what traditional methods cannot. Her central insight — that we must shift from constraining how an AI thinks to constraining the space in which it can act — is one I find myself returning to constantly in my own work at the intersection of AI and financial markets. Concise, rigorous, and quietly radical.

Daniele Grassi, CEO & Co-Founder Axyon AI