GIDS news media, articles, insights and virtual events educate and illuminate its audiences so they can be fully prepared to deal with the new realities at work and in their professions.
Get the latest event updates, and insights from today's leading voices.
< session />
Tue, April 27Architecture & Distributed SystemsAI-Native Software
Most software architectures assume that system behaviour is largely determined before deployment. Agentic systems challenge that assumption. When reasoning, tool selection, planning, delegation, recovery, and coordination happen at runtime, teams need to decide which decisions should remain deterministic and which should become part of an adaptive agent runtime.
In this session, you will explore the architectural layer between a business requirement and a production-ready agentic system. You will examine how to translate requirements into workflows, execution loops, tools, context boundaries, handoffs, evaluation points, and failure-handling paths, while avoiding brittle chains of prompts, rules, and hard-coded orchestration logic. You will also explore which behaviour belongs in application code, which requires an agent loop, where runtime decisions should occur, and how the surrounding harness can constrain, observe, and guide the system. The focus is on the architectural decisions that determine whether agentic systems remain understandable, adaptable, and operable as requirements, tools, data, and failure modes change.
What You Will Learn
How to translate business requirements into agentic workflows, execution loops, context boundaries, and failure-handling paths
How to determine which behaviour belongs in application code, runtime execution, and agent loops
How to decide when static orchestration is sufficient and when the architecture needs to support more adaptive execution
Who Should Attend
Software Architects, Software Engineers, AI Engineers, Technical Leads, Staff and Principal Engineers, Platform Engineers, and Engineering Managers designing intelligent systems.
< speaker_info />
Nicole Koenigstein is an AI Researcher and Practitioner in Agentic Systems, working across research, consulting, teaching, and direct system implementation to build reliable, production-ready AI systems. Her work focuses on multi-agent architectures, evaluation, safety, and long-term system behavior.
She served as an external evaluator for a European Commission AI Grand Challenge and has advised IOSCO on generative AI in regulated environments. She also serves on advisory boards for leading AI and quantitative finance conferences. Nicole regularly delivers invited talks and technical workshops across academia, industry, and international events. She is the author of Math for Machine Learning and Transformers in Action with Manning Publications. Her books Transformers: The Definitive Guide: Applications Beyond NLP and AI Agents: The Definitive Guide have been published by O’Reilly Media, and her forthcoming book Harness Engineering for AI Agents will also be published by O’Reilly Media.
