Notifications
Clear all
Topic starter
Hi everyone,
This is an expanded version of a previous question I posted, concerning the integration of document retrieval with user data collection.
I'm currently building a system that aims to retrieve document information while simultaneously collecting user data in a natural, conversational manner. I have successfully set up two distinct workflows:
- A workflow for retrieving document information using a Conversational AI agent.
- A separate workflow for collecting user data, which utilizes a different AI agent and stores the information in a database.
While both workflows operate effectively on their own, I'm facing challenges in merging them into a single, unified process. The primary hurdle is integrating the Conversational AI agent for document retrieval with the distinct AI agent responsible for user data collection.
I'm looking for advice on how to best combine these workflows to ensure a smooth user experience. Any insights into structuring this integrated flow would be highly valuable. Please let me know if you require any further details about my current setup or specific needs.
Information on your callin.io setup
- callin.io version: Version 1.75.2
- Database (default: SQLite): PostGre
- callin.io EXECUTIONS_PROCESS setting (default: own, main): default
- Running callin.io via (Docker, npm, callin.io cloud, desktop app): Docker
- Operating system: ubuntu
Posted : 31/01/2025 6:16 am
Hey,
One thing I find extremely useful is creating sub-workflows and treating them like functions.
With this approach, AI agents can call these “functions” using the Call Workflow tool, sending data that can go through multiple processes — allowing you to essentially build an entire backend system on top of this logic.
Think of it like a master function that works as a router, deciding the flow of information dynamically.
If you scale this idea to 2, 3, 4, or even more levels deep, you can create something like this:
- Router → User asks about heart diseases → Retrieve documents on that topic → Check patient’s data for heart-related exams → Respond with a clarifying question → Add a note to the patient’s file mentioning concern about heart issues → Ask if they want to schedule an appointment → Send all gathered information to the doctor.
This kind of structure makes complex interactions manageable and modular.
.
If my reply answers your question, please remember to mark it as a solution.
Posted : 12/03/2025 8:04 pm
This thread was automatically closed 90 days following the last response. New replies are no longer permitted.
Posted : 10/06/2025 8:05 pm