### Answer --- There's a way to monitor what the agent is saying in real-time using the

transcript_updated

webhook event. This event is triggered on turn-taking transcript updates, plus a final update when the call ends, and includes the full call data plus

transcript_with_tool_calls

. [(1) ]() However, the available sources don't describe a built-in feature to redirect or intervene in what the agent says mid-call. The webhooks provide real-time visibility into the conversation but are designed for monitoring and triggering external workflows rather than live agent control. For real-time transcript monitoring, you would: 1. Register a webhook with the

transcript_updated

event 2. Receive updates as the conversation progresses If you need to actively redirect calls, the warm transfer feature allows the AI to hand off to a human agent during a call. [(2) ]() Check out these potentially useful sources: - [Webhook Overview]() - [AI Voice Agents in 2025]() - [Retell AI Webhooks]() Would you like me to try to answer generally based on my knowledge, or do you have a specific use case in mind?

​ To learn more, see the sources I considered: [[1] Webhook Overview](https://docs.retellai.com/features/webhook-overview) [[2] AI Voice Agents in 2025: Everything Businesses Need to Know | Retell AI](https://www.retellai.com/blog/ai-voice-agents-in-2025) ​

Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.

Is the warm transfer only able to handoff to humans not an agent? @AI Evy

### Answer Based on the available sources, warm transfer is designed to hand off calls to human agents, not to another AI agent. [(1) ]() The warm transfer feature includes human detection — the AI confirms that a human has answered before completing the transfer, preventing failed connections and ensuring the caller isn't dropped into voicemail or a dead line. Key warm transfer capabilities that indicate human-focused design: - **Automatic Human Detection**: The AI verifies a human has answered before completing the transfer - **Whisper Messages**: The AI delivers a private context summary to the receiving human agent before connecting the caller - **Agent Detection Timeout**: Configurable timeouts control how long the AI waits for the agent to pick up The documentation consistently refers to transferring to "live agents," "human agents," or "fraud specialists" rather than other AI agents. [(1) ]() [(2) ]() [(3) ]() If you need to chain AI agents or route between them, that would likely require a different approach (such as using webhooks or custom logic) rather than the warm transfer feature specifically.

Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.

​ To learn more, see the sources I considered: [[1] Warm Transfer vs Cold Transfer - The AI Advantage in Call Centers | Retell AI](https://www.retellai.com/blog/effortless-handoffs-with-retell-ais-warm-transfer-feature) [[2] ](https://www.retellai.com/resources/retell-ai-fraud-alert-engine-voice-biometrics-warm-transfers-chargeback-reduction) [[3] What is Call Center Automation: The 2026 Guide That You Actually Need | Retell AI](https://www.retellai.com/blog/call-center-automation) ​