Register
As enterprises increasingly adopt multi-agent systems (MAS) for complex AI solutions, engineers face the dual challenge of scaling these systems while maintaining ethical responsibility. Traditional approaches often fall short when agent interactions multiply, leading to emergent behaviors that can amplify biases or create unintended consequences at scale.
This talk delves into the engineering principles and design patterns that enable responsible scaling of MAS. We'll explore how systems thinking informs architectural decisions, from designing modular agent components to implementing distributed governance mechanisms. Using examples and architectural diagrams, we'll demonstrate how to build scalable oversight for responsible AI into the core of MAS design.
Key takeaways include:
- Concrete design patterns for building scalable, self-regulating agent networks
- Techniques for dynamically adjusting agent behavior based on system-wide feedback
- Practical approaches to monitoring and debugging emergent behaviors in MAS
Attendees will gain a deeper understanding of how to leverage systems thinking to create multi-agent architectures that scale responsibly.
Speaker
Nimisha Asthagiri
Principal Data & AI @Thoughtworks | Consulting CTO & Strategist | Previously Chief Architect @edX
Nimisha Asthagiri is a Data and AI Principal at Thoughtworks, a global digital consultancy that integrates strategy, design and engineering to transform enterprises to modern digital businesses. She leads Data and AI transformations for her clients with strategic combinations of design thinking, change management, experimentation, and platform architecture. Her most recent focus is designing agentic enterprises for responsible AI. Prior, she was Chief Architect at edX, driving intentional architecture for the next generation of large-scale online learning. She is a long-term technologist who values innovations that result from the amplification of diverse voices and the synergism of collective strength.
