Skip to content

Automation · Customer service and scheduling

Log service requests on WhatsApp and answer their status with your Softr database

An AI agent logs the requests that come in on WhatsApp in your Softr database and answers their status when the customer asks.

How do I log the requests I get on WhatsApp in Softr and tell customers how they are going?

A Met connected to Softr finds the database and table where your team keeps service requests, reads its fields and, when a customer asks for something on WhatsApp, checks whether they already have an open request before creating another. If they do not, it creates the record with their name, phone number and request, and confirms it was logged. When the customer asks again, the Met finds their record by phone number, opens it and answers with the status your team set. Whatever is not in the table, the Met does not know, and each search returns up to 200 records.

What starts it

When the customer writes

It starts when a customer writes on WhatsApp to ask for a service or about a request they already made. There is no trigger to configure: the Met assigned to the line runs the procedure inside that conversation.

Nothing to set up. The Met assigned to that channel picks up the conversation and runs the procedure inside it.

Who runs it

Support Met with requests in Softr

Customer service team

This is not a named, seeded Met. It is the Met that already answers the business's WhatsApp, with Softr connected. Its work ends when the customer's request is logged in the table, or when the customer knows the status of the one they already had.

Run by the customer support Met

Channels: WhatsApp

What you need connected

6 steps · 6 tools

The procedure, step by step

Each step shows the tool that runs. They belong to the real connector: if one of them stopped existing, this page would not build.

  1. 1

    Find the requests database

    The Met lists the databases the token can reach and keeps the one the skill names, for example "Services", without touching the others.

  2. 2

    Find the right table

    Inside that database, the Met lists the tables and picks the requests one. That way it does not write to the customers or inventory table by mistake.

  3. 3

    Read the table's fields

    In Softr, records come back keyed by field ID, not by field name. The Met reads the table's fields to know which one is the phone number, the service and the status.

  4. 4

    Check whether the customer already has a request

    Before creating anything, the Met searches records by the customer's phone number. If it finds an open request, it answers about that one instead of duplicating it.

  5. 5

    Create the new request

    If there is no open one, the Met creates the record with the name, phone number, requested service and date, and confirms to the customer that it was logged.

  6. 6

    Answer the status when asked

    When the customer writes again, the Met opens their record and tells them the status and the note your team left, without inventing a date that is not in the table.

Before you start

What you need ready

The Met solves none of these for you. If one is missing, the automation stops there.

The limits

What this automation does NOT solve

Better said here than discovered halfway through the rollout.

FAQ

Questions about this automation

The phone search does not find them and the Met may create a new request. If your table stores another detail, such as email or an ID number, the skill can search by that too.

Yes: the Met creates the record in the same table your Softr apps use, so it shows up where your team already works.

It could update the status field with the update-record action, which comes switched on, but this procedure leaves it to your team so the status is always the real one. If you do not want it to, switch it off in Connections.

Edit data on the requests database, so the Met can create records. With view only, the Met answers statuses but does not log anything new.

Keep going

Other automations built on the same tools

Want this automation running on your own data?

We will show it to you with your accounts connected, not with a canned demo.