Hello,
I’m currently working on a project for a hotel system that operates entirely through voice.
The idea is:
- I first communicate with ElevenLabs.
- ElevenLabs processes and understands my question.
- A webhook is then triggered to send my question to an AI agent.
- After a short wait, the AI agent responds, and the reply is sent back to the last node, while the call remains active on ElevenLabs.
However, the problem I’m facing is:
When I ask a second question, it can’t properly access the AI agent again.
I really need help figuring this out. 
Also, if there’s a better way to structure the system, I’d love suggestions!
What do you mean by:
When I ask a second question, it can’t properly access the AI agent again.
The agent responds with an error? Or no response? Or do you mean it doesn’t have the context of the previous question? (You would use memory for that in some way)
What do you mean by:
asking elevenlabs a question
Do you mean sending a query for it to it or using the agents/conversation ai feature? Can you show some screenshots of the setup on elevenlabs side?
I mean
I have connected the AI agent elevenlabs to the webhook, so this agent in elevenlabs has a tool called n8n and has only one parameter, the user question, and I give him instructions that when he receives the user question it goes to n8n the webhook actually and post the question (this is just the beginning of the idea it should be improved)
Then the llm answer and give the answer to the response webhook
So what am I actually doing is I start the workflow in n8n and then start calling the ai agent in elevenlabs at the same time so when I give agent a question it starting the webhook and generating an answer but that’s only happen once which I mean the call is remaining in elevenlabs but when I ask another question for example ask whats the type of the room number…
it can ask the llm again
I hope you understand me:
This video is similar to what I did: https://youtu.be/pJYm7MOyMH0?si=WjbiyTJLzFgwuaeS
