Automation · Customer service and scheduling
Log in GitHub the bug a customer reports on WhatsApp and tell them which release shipped the fix
An AI agent logs in GitHub the bug a customer reports, avoids duplicates and tells them which published release shipped the fix.
How do I tell a customer on WhatsApp which version of my app fixed their bug?
When a customer reports a bug in your app or site on WhatsApp, the Met searches the repository for an issue with that problem. If one exists, it adds a comment with the new report; if not, it creates the issue with what the customer said and gives them the number. When the customer asks again, the Met reads the issue: if it is still open, it says so; if it was closed, it reviews the pull request that closed it, searches the published release notes for the one that includes that change and answers which release shipped it, or that the fix is not published yet.
What starts it
When the customer writes
It starts when a customer writes on WhatsApp to report a bug or ask whether it was fixed. 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 follows bugs in GitHub
Customer service team
This is not a named, seeded Met. It is the Met that already answers the business's WhatsApp, with GitHub connected: its work ends when the customer has their report number or knows which release shipped the fix.
Run by the customer support Met
Channels: WhatsApp
What you need connected
- GitHub Automate and collaborate
5 steps · 7 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
Check whether the bug is already reported
The Met searches the app's repository, with a natural language query, for issues that describe the same bug. If it finds one, it adds a comment with the new report.
- 2
Create the issue
If there is no similar one, the Met creates the issue with a clear title, the customer's description and the steps they described, and sends the customer the issue number on WhatsApp.
- 3
Check the issue status
When the customer asks whether it is fixed, the Met reads the issue. If it is still open, it says the team is still working on it; if it is closed, it looks at which pull request closed it.
- 4
See when the fix went in
The Met opens that pull request and reviews its details to learn whether it was merged and on what date, before looking for the release that includes it.
- 5
Find the published release
The Met gets the latest published release and lists the earlier ones, and searches their notes for the issue or pull request number. It tells the customer which release shipped the fix, or that it is not in any published release yet.
Before you start
What you need ready
The Met solves none of these for you. If one is missing, the automation stops there.
-
A repository where the team logs bugs
Your team uses the GitHub issues of the app's or site's repository. If it publishes releases with notes, the Met can tell the customer which one shipped the fix.
-
GitHub connected in Met with a personal token
In GitHub, create a personal token with access only to that repository. In Met, open Connections → GitHub → Connect and paste it. Creating issues and commenting stay on unless the admin turns them off.
-
A WhatsApp line with the Met assigned
The business connects its WhatsApp Business API line and assigns the Met that serves customers. The report and the answer happen inside that conversation.
The limits
What this automation does NOT solve
Better said here than discovered halfway through the rollout.
-
It does not fix the bug. It logs and follows it; fixing the code and publishing the release is your team's work.
-
It does not guess the release. If the release notes do not mention the issue or the pull request, the Met tells the customer it cannot confirm yet which one shipped it.
-
It does not ask for confirmation in the chat before creating the issue or the comment: if the actions are on, it runs them. The admin decides in Connections which ones stay on.
-
It does not show the customer the code or the team's internal comments: it answers with the status and the release, in plain words.
FAQ
Questions about this automation
The Met can still say whether the issue is open or closed and whether the pull request was merged. What it cannot do is name the release, because it does not exist in GitHub.
Only if the repository is public. In a private repository, the customer learns everything on WhatsApp and never needs a GitHub account.
The Met finds the existing issue and adds a comment for each new report, so your team sees how many people have the problem without duplicate issues.
Keep going
Other automations built on the same tools
Customer service and scheduling
Open a Linear issue from a customer report on WhatsApp and tell them how it is going
How do I make customer reports on WhatsApp arrive in Linear as issues?
Customer service
- Starts:
- when the customer writes
- Steps:
- 5, with 6 real tools
- Needs:
- Linear
Customer service and scheduling
Open a Freshdesk ticket from WhatsApp and tell where it stands
How do I turn a complaint that arrives on WhatsApp into a Freshdesk ticket without copying it by hand?
Customer service
- Starts:
- when the customer writes
- Steps:
- 5, with 10 real tools
- Needs:
- Freshdesk
Customer service and scheduling
Open a Gorgias ticket from WhatsApp and escalate it to the team that solves it
How do I move a complaint that arrives on WhatsApp into Gorgias without copying it by hand or losing what the customer said?
Customer service
- Starts:
- when the customer writes
- Steps:
- 5, with 7 real tools
- Needs:
- Gorgias
Customer service and scheduling
Open a Jira issue from a report that comes in on WhatsApp and answer how it is going
How do I make customer reports on WhatsApp arrive in Jira as issues?
Customer service
- Starts:
- when the customer writes
- Steps:
- 5, with 6 real tools
- Needs:
- Jira y Confluence
Want this automation running on your own data?
We will show it to you with your accounts connected, not with a canned demo.