Ai system design

Building AI Agent Systems and Scaling Challenges in Agentic AI

Building AI Agent Systems and Scaling Challenges in Agentic AI

Scaling agentic AI systems presents unique challenges beyond traditional software scaling. This summary explains why expanding a single agent's capabilities leads to non-linear increases in cost, latency, and failure propagation. The talk frames this as a systems design problem solved by moving from a monolithic agent to a multi-agent architecture with distributed responsibilities, and it explores the critical architectural trade-offs between horizontal and vertical scaling of agent capabilities.

Agentic Al in SW Development: Evolving Patterns & Protocols • Bhuvaneswari  Subramani • GOTO 2025

Agentic Al in SW Development: Evolving Patterns & Protocols • Bhuvaneswari Subramani • GOTO 2025

Bhuvaneswari Subramani details the "Agentic Shift" in AI by presenting an evolutionary journey through seven foundational system design patterns. The talk progresses from simple conversational clients to sophisticated, multi-agent systems, covering key patterns like Retrieval-Augmented Generation (RAG), Self-Correcting RAG, and the Model Context Protocol (MCP), explaining how each pattern adds new layers of context, action, and autonomy.