### Answer --- To filter spam calls before your agent answers, you can use inbound webhook filtering. [(1) ]() Here's how it works: 1. Enable an inbound webhook on your phone number 2. Check the

from_number

in the webhook payload and reject suspicious calls by responding with a

200

status without including

override_agent_id

Additional mitigation strategies: - Add detection logic in your agent prompt to identify repeated or bot-like audio patterns and hang up quickly - Rate limit by phone number or IP - Use user identification if possible - Configure rules at your SIP provider level to block known spam numbers Note that Retell doesn't currently auto-detect prerecorded or bot audio, so mitigation needs to be handled via webhooks, SIP provider rules, or agent prompt logic. For more detailed webhook configuration, check out [Webhook Overview]() . [(2) ]()

​ To learn more, see the sources I considered: [[1] Spam attack on AI Voice Agent - repeated audio from multiple numbers](https://discord.com/channels/1186424376300679209/1450431147929768019) [[2] Platform Changelogs | Retell AI](https://www.retellai.com/changelog) ​

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