Developing AI applications goes beyond single-model interactions. We're seeing a shift towards agentic AI systems, where multiple specialized agents work together. While there’s a myriad of vendor-backed solutions, the real challenge for an AI architect lies in effectively building, orchestrating, and deploying these custom, collaborative systems to production.

Given the diverse and complex tasks these systems handle, a "one-size-fits-all" approach to coordination just doesn't work. We'll explore the spectrum of agentic patterns, from reliable but rigid workflows to highly flexible, autonomous agent orchestration using LLMs, and everything in between.

we'll cover:
* How to build and deploy custom agents
* Various agentic AI patterns to coordinate these agents
* How to combine these patterns
* Production considerations for agentic systems, including deployment to platforms like Kubernetes or even Serverless environments, and essential concerns such as observability and resilience.