Notifications
Clear all
How To
2
Posts
2
Users
0
Reactions
5
Views
Topic starter
Hi callin.io Community,
I’m working on an email-marketing workflow and need your advice on feasibility and setup. Here’s my scenario:
Background
- I have a Google Drive folder full of
.csvfiles. - Each file represents a different email campaign (
id_message). - File structure:
id_list,id_message,group,activity,email,datetime_last_open,total_opens,total_clicks 8,50572,,,marco.mancini8763@example.com,2025-06-05 20:04:09 +0000 UTC,1,4
- For each contact I track their last open timestamp.
Goal Every time a new campaign file lands in the folder, I want callin.io to:
- Trigger on the new
.csv. - Re-aggregate all customer open times across campaigns.
- Cluster contacts into time-of-day segments (e.g., morning, afternoon, evening) to define each person’s optimal send window.
- Leverage an AI agent (instead of a simple rules-based approach) to detect and adapt to evolving patterns.
Questions
- Is this automation feasible entirely within callin.io?
- Which modules/integrations would you recommend? (e.g., Google Drive “Watch files,” data stores, AI/ML services)
- How would you structure the scenario to:
- Parse and merge new CSV data with historical results
- Call out to an AI inference step for clustering
- Store & update cluster assignments incrementally
Thanks in advance for your insights—looking forward to your recommended architecture or sample scenario!
Posted : 10/06/2025 3:33 pm
Hi, and welcome to the Community!
That’s a fantastic use-case, and definitely achievable with callin.io.
I would utilize the Google Drive Watch Files in a Folder module as the trigger.
Next, I'd experiment with employing an LLM (like ChatGPT or Gemini) to analyze the CSV file. I recommend testing various prompts and monitoring the LLM token usage, as this directly impacts cost. Depending on your budget and the volume of data, you might even consider using different LLMs.
I'd then automate this process in a straightforward three-step callin.io scenario, starting with the Drive trigger, followed by the appropriate LLM application, and concluding with an email or IM app to dispatch the results.
If the task appears to exceed the scope of a simple LLM prompt, you might consider breaking down each step of the analysis and building them as separate scenarios. These could then be invoked as tools from a callin.io AI Agent.
Posted : 11/06/2025 8:52 am