I don’t know if there are already projects similar to this one, but I haven’t found any.
My idea is:
The user accesses the chat looking to solve a problem. By default, they chat with an AI with a knowledge base to get answers.
But in my scalable architecture, I want other teams to develop workflows or tools that solve or help the user in the best way possible with specific problems.
I figured that an AI agent with all these workflows in the tools could become cumbersome and the AI might not be able to handle them all or choose the best option efficiently (I’m not sure if I’m right).
So I’m trying to imagine a workflow like the one below:
the user is directed by default to the AI agent with KB and a tool that checks the database to see if a specific workflow has already been developed to solve the problem. If so, it sets a new chat mode in redis to direct new messages (this has a problem in that I don’t execute the new workflow, I have to wait for another message from the user).
These specific workflows can execute other AI agents that interact with the user.
I don’t know if my idea is clear, but I would like ideas or workflows that can help me with this.
Is there a more efficient way to deal with this that is scalable (my teams can easily run their workflows)?
Perhaps a single AI agent with the workflows in the tools would work well? Will it be able to direct the flow of messages at the right time? I don’t know…
Describe the problem/error/question
What is the error message (if any)?
Please share your workflow
Share the output returned by the last node
Information on your n8n setup
- n8n version: 1.106.3
- Database (default: SQLite):
- n8n EXECUTIONS_PROCESS setting (default: own, main):
- Running n8n via (Docker, npm, n8n cloud, desktop app): Docker self-hosted
- Operating system: MacOS 15.6.1