Govern AI Costs in Real Time: Hands-On with agentgateway
AI applications can generate unpredictable costs, especially when agents and automated workflows make thousands of LLM calls. In this hands-on workshop, you'll build a cost-governance layer using agentgateway's External Processing (ExtProc) framework to track usage, enforce budgets, and prevent runaway spending before requests reach an LLM provider.
You'll learn how to:
- Enforce AI budgets and spending limits at the gateway
- Attribute costs to teams, applications, and models
- Implement pre-request budget checks and cost settlement
- Block or throttle requests when limits are reached
- Apply governance without modifying application code
You'll leave with:
- A working AI cost-control implementation
- Practical patterns for governing AI spend across agents, copilots, and AI applications
AI applications can generate unpredictable costs, especially when agents and automated workflows make thousands of LLM calls. In this hands-on workshop, you'll build a cost-governance layer using agentgateway's External Processing (ExtProc) framework to track usage, enforce budgets, and prevent runaway spending before requests reach an LLM provider.
You'll learn how to:
- Enforce AI budgets and spending limits at the gateway
- Attribute costs to teams, applications, and models
- Implement pre-request budget checks and cost settlement
- Block or throttle requests when limits are reached
- Apply governance without modifying application code
You'll leave with:
- A working AI cost-control implementation
- Practical patterns for governing AI spend across agents, copilots, and AI applications
