Stop restricting the agent. Start restricting its environment.

Thanks to visagarwal​ for co-authoring this post. Cross-posted from: https://commandline.microsoft.com/azure-sre-agent-restricting-environment-ai-safety/ Azure SRE Agent gives an LLM tools, a code execution environment, and access to production resources. The first question most people ask is: “How is that safe?” The instinctive answer is to restrict the agent.