Summary
The new products route model calls through a central control plane with token-spend visibility, rate limits, budget controls and provider failover. Fastly’s AI Firewall is designed to detect prompt injection and other attacks in the request path, while API Security can block agent requests that violate API contracts.
Why it matters
AI infrastructure is moving from model access toward runtime governance, with security, cost control and agent authorisation enforced at production traffic boundaries.
Related coverage
- Huawei launches Fintelligent AI stack for financial institutions
- Veeva introduces an agent for biopharma safety and quality triage
- US proposes an AI incident alert mechanism with China