Build WhatsApp support and application tracking in n8n

A consulting firm used n8n agents to answer WhatsApp questions, gather intake details, read uploads, and keep clients updated on application status.

Done with n8n· Advanced

What they did
They set up five agents in n8n: one for client messages, one for reading documents, two for tracking application progress for users and admins, and one supervisor. The workflows tied into WhatsApp, Google Drive, and email, while a separate database kept chat context because n8n does not retain it on its own. They also added custom Python for document search and a queue so the supervisor could route uploads to the right worker.
How it went
The build showed how to combine n8n with outside pieces for a small support operation. It did not report usage counts, accuracy, or client outcomes, and it also did not test the system at larger scale.
Tips
Plan on adding your own state store, queue, and retrieval layer if you want a similar setup. n8n by itself is not a good fit for heavy traffic or vector storage.

Try it yourself with n8n

Set up an n8n workflow for my [business type] that handles WhatsApp messages any time of day, asks for [required intake details], reads uploaded [PDFs/photos/docs], saves the extracted information to [storage target], and updates the client when their case reaches [status stages]. Before any message is sent outward, show me the exact text for approval, and stop after one test case has moved from intake to a status change.

Fill in the [brackets]. Agents can make mistakes, so review anything before it is sent, paid or deleted.

Read the original on dev.to ↗

Get 3 agent uses like this every morning

With the day's top AI news. Free, and one click to unsubscribe.