This question originally came up in our Slack community and the thread has been consolidated here for long-term reference.
I’m searching for a way to prevent an agent from being interrupted at the beginning of an AgentSession when using a realtime model.
Due to legal reasons, we need to ensure the agent is not interrupted when starting the conversation after a participant joins. The agent must explain that the human is speaking to an AI, and we don’t want interruptions during this explanation.
Is there a way to achieve this?