---
title: AI Runtime Control
summary: null
url: https://www.fastly.com/documentation/solutions/tutorials/ai-runtime-control
---

Learn how to use AI Runtime Control (ARC) to manage and monitor the AI traffic your applications and developers send to LLM providers.

- [Cap what your team spends on AI with AI Runtime Control](https://www.fastly.com/documentation/solutions/tutorials/ai-runtime-control/cap-team-ai-spending/) - Use AI Runtime Control (ARC) to keep a team's AI spending predictable by setting a warning limit, a hard stop, and a rate limit on each engineer's virtual key.
- [Connect AWS Bedrock to AI Runtime Control with an IAM role](https://www.fastly.com/documentation/solutions/tutorials/ai-runtime-control/connect-aws-bedrock-with-an-iam-role/) - Use AI Runtime Control (ARC) to call models on AWS Bedrock without storing long-lived AWS credentials by allowing ARC to assume an IAM role in your AWS account.
- [Connect Google Vertex AI to AI Runtime Control with Google Cloud IAM](https://www.fastly.com/documentation/solutions/tutorials/ai-runtime-control/connect-google-vertex-ai-to-arc-with-google-cloud-iam/) - Use AI Runtime Control (ARC) to call models on Google Vertex AI without storing long-lived Google Cloud credentials by allowing ARC to impersonate a service account in your Google Cloud project through workload identity federation.
- [Keep AI traffic flowing with failover providers in AI Runtime Control](https://www.fastly.com/documentation/solutions/tutorials/ai-runtime-control/set-up-failover-ai-providers/) - Use AI Runtime Control (ARC) to keep requests flowing when a provider has trouble by configuring a second provider that serves the same model as a backup.
- [Track per-engineer AI usage with AI Runtime Control](https://www.fastly.com/documentation/solutions/tutorials/ai-runtime-control/track-per-engineer-ai-usage/) - Use AI Runtime Control (ARC) to track how much each engineer uses Claude Code by issuing a virtual key per person and reading the usage ARC records for each one.
