# AI
_All AI Videos_
[__
Intelligent routing reduces LLM session costs by picking the lowest-priced capable model at cost seams and respecting cache locks to keep quality intact.
__](/resources/videos/intelligent-routing-llm-cost)__Intelligent routing reduces LLM session costs by picking the lowest-priced capable model at cost seams and respecting cache locks to keep quality intact.
__
[__
How to Automate Continuous Training for AI Agent Skills
__](/resources/videos/ai-agent-skill-training)__How to Automate Continuous Training for AI Agent Skills
__
[__
Production AI Models Run on a 90-Component End-to-End Infrastructure Ecosystem
__](/resources/videos/production-ai-infrastructure)__Production AI Models Run on a 90-Component End-to-End Infrastructure Ecosystem
__
[__
An AI Registry Lets Developers Instantly See Which APIs, Models and Tools They Can Use
__](/resources/videos/ai-registry-agentic-enablement)__An AI Registry Lets Developers Instantly See Which APIs, Models and Tools They Can Use
__
[__
From APIs to AI Agents: Building Real AI Workflows with Kong
__](/resources/videos/apis-to-ai-agents-kong-gateway-oidc-mcp-tools)__From APIs to AI Agents: Building Real AI Workflows with Kong
__
[__
Context‑Aware LLM Traffic Management with RAG and AI Gateway
__](/resources/videos/rag-kubernetes-kong-ai-gateway-kaido)__Context‑Aware LLM Traffic Management with RAG and AI Gateway
__
[__
Keynote: No AI Without APIs
__](/resources/videos/apis-powering-ai-revolution)__Keynote: No AI Without APIs
__
[__
Keynote: Building for the New AI Era
__](/resources/videos/future-kong-developer-tools)__Keynote: Building for the New AI Era
__
[__
Keynote: Fireside Chat with Goldman Sachs
__](/resources/videos/goldman-sachs-ai-api-convergence-business-clients)__Keynote: Fireside Chat with Goldman Sachs
__
[__
Kongfidential Computing
__](/resources/videos/apis-ai-integration-high-trust-environments)__Kongfidential Computing
__
[__