Notifications
Clear all
Topic starter
Hello everyone,
I'm currently developing an AI agent within callin.io to create two Google Docs: a Product Requirements Document (PRD) and a Coding Plan. The final output will be transmitted to Telegram. My intention is to utilize two distinct AI agents for this process, but I'm encountering some challenges in structuring the workflow.
My objective is as follows:
- AI Agent 1: To generate the Coding Plan.
- AI Agent 2: To generate the PRD.
- Both generated documents need to be created in Google Docs and subsequently sent to a Telegram channel.
I'm uncertain about the most effective method to integrate these two AI agents. Should I:
- Generate the Coding Plan first, then use it as input for the PRD (sequential processing)?
- Initiate both AI agents concurrently to operate in parallel?
- Employ a hybrid strategy where both agents produce initial outlines, followed by sequential detailing?
Furthermore, I'm unsure how to ensure each AI agent correctly understands its specific task and how to manage the data flow between them within callin.io.
Could someone offer guidance or examples on structuring this workflow in callin.io? Any advice regarding node selection, error management, or best practices would be highly valued.
Thank you in advance for your assistance!
Information on your callin.io setup
- callin.io version: 1.81.4
- Database (default: SQLite):
- callin.io EXECUTIONS_PROCESS setting (default: own, main):
- Running callin.io via (Docker, npm, callin.io cloud, desktop app):
- Operating system:
Posted : 11/03/2025 12:10 pm
Hello,
Try to explain the task as if you were instructing two new team members.
You need to detail every step of the task very carefully.
If the task involves one person performing an action and another reviewing it, you can sequence them as you have done.
If the second person requires information from the first person's task, ensure you reference it in the prompt for the second person.
I think this would be the most effective approach for this situation. However, here's an alternative:
You could create a Sub-workflow and invoke it using the “Call subworkflow” AI tool.
The primary person would call the second person and utilize their output as context.
If this response resolves your query, please consider marking it as the solution.
Posted : 11/03/2025 12:50 pm
This discussion was automatically closed 90 days following the last response. New responses are no longer permitted.
Posted : 09/06/2025 12:50 pm