Skip to content

Automation · Customer service and scheduling

Open a Jira issue from a report that comes in on WhatsApp and answer how it is going

An AI agent checks Confluence, avoids duplicates, opens the issue in Jira and tells the customer what status their case is in.

How do I make customer reports on WhatsApp arrive in Jira as issues?

When a customer reports a problem on WhatsApp, the Met finds your Atlassian site, searches Confluence for a documented solution and, if there is one, replies with it. If not, it searches Jira for a similar open issue so it does not duplicate it; if one exists, it adds a comment with the new report, and if not, it creates an issue in the support project with what the customer said. It gives the customer the case key. Days later, when they ask how it is going, the Met gets the issue by that key and replies with the status and the latest comment.

What starts it

When the customer writes

It starts when a customer writes on WhatsApp to report a problem or ask about an open case. There is no trigger to configure: the Met assigned to the line handles it in 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 that logs cases in Jira

Customer service team

This is not a named, seeded Met. It is the Met that already answers the business's WhatsApp, with Jira and Confluence connected: its work ends when the customer has the documented solution or their case key, or when it tells them how it is going.

Run by the customer support Met

Channels: WhatsApp

What you need connected

5 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 Atlassian site

    The Met lists the Atlassian sites the connected account can access and takes your company site's cloudId. Atlassian needs it before any other tool.

  2. 2

    Look for a documented solution

    The Met searches Confluence, with a CQL query, for the page that explains that problem. If it exists, it replies to the customer with the page's steps and does not open a case.

  3. 3

    Check whether a similar issue exists

    The Met searches Jira, with JQL, for open issues in the support project with the same problem. If it finds one, it adds a comment with the new report instead of duplicating it.

  4. 4

    Create the issue

    If there is no similar one, the Met creates the issue in the support project with a summary, the customer's description and phone number, and sends the customer the case key on WhatsApp.

  5. 5

    Answer how the case is going

    When the customer asks about their case, the Met gets the issue by its key and replies with the current status and the team's latest comment. If there is no news, it says so.

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

No. The customer only talks to the Met on WhatsApp; the issue is created by the account that connected Jira in Met.

Yes, if those fields exist in your project and can be edited. Put it in the Met's instructions so it always uses the same type.

The Met can search with JQL for issues that have their phone number or name in the description, and confirm with the customer which one it is.

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.