On Demand: 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
Speakers
Sebastian Maniak
Sebastian Maniak is an AI Architect at Solo.io, where he focuses on go-to-market for AI connectivity — agent gateways, LLM security, and the infrastructure that makes agentic systems deliverable, secure, and operable in the enterprise. He is also a professor of network and cybersecurity at Sheridan College, teaching Applied Network Security and Infrastructure as Code. He brings more than two decades of experience in application delivery, security, and automation — from F5, Fortinet, and HashiCorp through cloud-native service mesh and API platforms — and now applies that same delivery-and-control mindset to Enterprise AI. Over his career he has worked across architecture, consulting, product, education, and content, which gives him a broad generalist’s view of how technical platforms actually get adopted.
Michael Levan
Focusing on providing business value through technology, working directly with customers, providing first-class advisory, and content, Michael Levan helps organizations address needs through Agentic AI practices. He has worked across industries as an engineer, consultant, trainer, and content creator. He's a CNCF Ambassador, AAIF Ambassador, 4x published author, international speaker, and was part of the Kubernetes v1.28 and v1.31 Release Teams. Michael's approach translates technical complexity into business value, delivering actionable solutions that enhance performance, security, observability, and agentic workloads.
