### Answer No, multi-prompt agents are not legacy [(1) ]() . Retell AI offers three current approaches for building conversational agents: Single Prompt, Multi-Prompt Tree, and Conversation Flow . Multi-prompt agents remain a supported and recommended option for certain use cases . They organize conversations into a structured tree of states, each with its own focused prompt and behavior . Each state includes focused prompts, state-specific functions, transition logic, and context preservation . Multi-prompt agents are best suited for complex conversations that would be difficult to manage with a single prompt . You should consider using a multi-prompt agent when your single prompt exceeds 1000 words or uses more than 5 functions . The benefits of multi-prompt structure include predictable behavior, easier debugging, better function control, scalable design, and improved team collaboration .

​ To learn more, see the sources I considered: [[1] Single/Multi Prompt Agent Overview](https://docs.retellai.com/build/single-multi-prompt/prompt-overview) ​

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

@AI Evy but it is legacy now in the retell ai platform https://cdn.discordapp.com/attachments/1513873765921194155/1513874595642609664/rn_image_picker_lib_temp_b2bb6bfb-a4b7-4db1-8b4d-d9a9492f9fa8.jpg?ex=6a295116&is=6a27ff96&hm=1180f51ba24ccc4506d5a9854e5772dd429cd0e314fb0605d68e97b13b512259&

### Answer Based on the available documentation, multi-prompt agents are not described as legacy in the Retell AI platform [(1) ]() . The official documentation presents three current agent architecture options: Single Prompt, Multi-Prompt Tree, and Conversation Flow [(1) ]() [(2) ]() . Multi-prompt agents are actively documented as a recommended approach for specific use cases [(1) ]() . They're best suited for complex conversations that would be difficult to manage with a single prompt, particularly when your single prompt exceeds 1000 words or uses more than 5 functions . The documentation shows that multi-prompt agents organize conversations into a structured tree of states, each with its own focused prompt and behavior . Each state includes focused prompts, state-specific functions, transition logic, and context preservation . Additionally, the API reference documentation includes current endpoints for working with multi-prompt agents, such as the Retell LLM endpoint that supports the

states

field for multi-prompt configurations [(3) ]() . If you have information suggesting multi-prompt agents are legacy that isn't reflected in the current documentation, I'd recommend reaching out to Retell AI support for clarification.

​ To learn more, see the sources I considered: [[1] Single/Multi Prompt Agent Overview](https://docs.retellai.com/build/single-multi-prompt/prompt-overview) [[2] Conversation Flow Overview](https://docs.retellai.com/build/conversation-flow/overview) [[3] Get Retell LLM](https://docs.retellai.com/api-references/get-retell-llm) ​

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