### Answer --- I don't have specific information in the available sources about blocking or filtering specific words from the agent's responses in Retell AI. However, based on the available documentation, here are approaches you could try: **Prompt-based instruction**: You can modify your agent's prompt or instruction to explicitly tell it to avoid using specific words. For conversation flow agents, you can update the

global_prompt

[(1) ]() [(2) ]() or individual node instructions [(3) ]() to include guidance like "Never use the word [specific_word]. Always use [alternative] instead." For conversation flow agents, you can update instructions at: - The global level using the

global_prompt

field [(1) ]() [(2) ]() - Individual conversation nodes using the

instruction

field [(3) ]() While this isn't a hard block, LLMs typically follow explicit instructions about word avoidance when clearly stated in the prompt [(4) ]() . For a more definitive solution or built-in word filtering features, I'd recommend: - Visit [Documentation]() - Visit [Hire certified Retell partner]() Would you like a general answer based on my knowledge of LLM behavior instead?

​ To learn more, see the sources I considered: [[1] Get Conversation Flow](https://docs.retellai.com/api-references/get-conversation-flow) [[2] Update Conversation Flow](https://docs.retellai.com/api-references/update-conversation-flow) [[3] Conversation Node](https://docs.retellai.com/build/conversation-flow/conversation-node) [[4] Large Language Model (LLM)](https://www.retellai.com/glossary/large-language-model-llm) ​

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