Agentic AI
The real fundamentals of AI system design
Getting started with governance for agentic AI
Agentic AI has captivated enterprises and computer science communities as the next frontier in artificial intelligence. However, the concept of AI agents isn't new. Multi-step systems have been used within academia and in targeted places in high-tech industries for decades.
The controversial idea in agentic AI is when an LLM is used as the main reasoning part with no clear way to govern the system. No matter what models make up your agentic system, you will need a strategic AI governance plan with specific capabilities and expertise.
How to build agentic AI systems the right way
Now that you’ve read about how to manage agentic AI, you might be wondering if there’s a way to build these systems more effectively from the start? You’re in luck. Listen to these four podcasts and gain an understanding of how to build and govern agentic AI systems.
What if we've been approaching AI agents all wrong? While the tech world obsesses over large language models (LLMs) and prompt engineering, there's a foundational approach that could revolutionize how we build trustworthy AI systems: mechanism design.
The hosts look at utility functions as the mathematical basis for making AI systems. They use the example of a travel agent that doesn’t get tired and can be increased indefinitely to meet increasing customer demand.
The third podcast in our series focuses on building agentic AI systems from the ground up and on how to achieve the desired accuracy. In this episode, we explore linear programming and optimization methods that enable reliable decision-making within constraints.
Sid and Andrew explore the unique governance challenges of agentic AI systems, highlighting the compounding error rates, security risks, and hidden costs that organizations must address when implementing multi-step AI processes.
Technical supplement: Building an AI agent that works
Are you responsible for making the math work behind your agentic AI systems? Then this technical guide to our episodes about building these systems the right way is for you.
Review this mathematical specification for Agentic AI Travel Agents. It combines microeconomics, mechanism design, and utility optimization to ultimately achieve accurate and cost-effective outcomes with governance in place.