Describe the problem/error/question
What is the error message (if any)?
Please share your workflow
(Select the nodes on your canvas and use the keyboard shortcuts CMD+C/CTRL+C and CMD+V/CTRL+V to copy and paste the workflow.)
Share the output returned by the last node
Information on your callin.io setup
- callin.io version:
- Database (default: SQLite):
- callin.io EXECUTIONS_PROCESS setting (default: own, main):
- Running callin.io via (Docker, npm, callin.io cloud, desktop app):
- Operating system:
Please provide the rewritten markdown content *it should be in the markdown format.
So, you could group the HTTP nodes into blocks of, say, 5 each, connect these to another AI agent or MCP server, and then have a main flow like the one above, which calls each MCP server/agent.
I'm thinking of a multi-layered AI agent setup, where the main AI agent calls the most relevant AI agent that has 5 tools (HTTP nodes)?
This approach might be effective; I haven't experimented with it yet.
How many HTTP requests do you intend to include? Are you experiencing any performance issues with the current setup?
I made a further post here about it too, Exploring Multi-Agent Patterns in callin.io Using MCP Triggers & Clients (Without Webhooks) This might help further.
Hello,
It seems the flow isn't completing.
You could try removing the connection to the edit node (to test the initial AI agent, and then connect the rest). I believe once it passes the switch, it should respond after further processing by other AI agents.
Hope this is helpful.
How can I connect the AI agent?
Can we resolve this via a Google Meet call?
Essentially, if I detach the switch node from the edit field, the AI agent will have restricted data available to respond to inquiries.
Correct — but you need to ensure it passes through the Switch node correctly.
That said, I’m still happy to assist where possible. Let me know if you’d like to troubleshoot further or schedule a call.
That's quite an unfounded accusation. It's unfortunate, but I hope the situation improves.
How can I resolve this? I've done everything I possibly could.
Are you available to connect right now?
Give me about an hour, and I'll send a reply or a direct message.
I'd really like to discuss this further, but honestly, I've already stated my position. I even had recent interviews with the team, and I felt that someone else was chosen because I wasn't active in the community. So, here I am.
Apologies for that. I'll be awaiting your feedback in an hour.
Hey, so I was thinking, if you want to share the workflow, I can help get it running for you, or perhaps via Discord? I usually meet on Google Meet, but I'm trying to avoid any potential issues. So, what I'm proposing is you can try uploading the workflow here, or send it via a private message.
I'll work on it to get it responding. I will provide details of what I did and share back the workflow if it's acceptable to you.
Let me know, as I should be free for the next few hours, then I'll be focusing on my workflows.
From what I can see, the main part is adding an output parser to your AI agent, ensuring the flow is continuous and filters correctly through sub-agent processing, and then returns to the chat once fully completed.
How can I share my workflow?