Track 9: LLM Engineering and Production, Cost, Caching and Routing
Where the Money Goes: Token Accounting
Attribute cost per user and per feature.
Get notified on YouTube Udemy certificate: coming soon
Course
Agent Observability & Cost Control
Udemy: coming soon
Tools
- Langfuse (open-source, freemium)
Watch first
In this module
- Where the Money Goes: Token Accounting
- Caching: Prompt Caching and Semantic Caching
- Model Routing, Cascades and Latency Engineering
- AI Gateways, Budgets and Kill Switches