/
/
Fix the BugHerd bugs that cost support the most
For teams planning web fixes who want open BugHerd bugs ranked by the Zendesk tickets they cause, by asking their AI assistant.
On this page
Connector
Connect BugHerd, pick your AI tool and paste the prompt.
The problem
Bug priority ignores how much support work they cause
The BugHerd backlog shows severity, but not how many customers a bug pushes into Zendesk. Counting that means reading linked tickets and searching for similar complaints per bug, so fixes are prioritised without knowing the support cost.
Without PopdockAI
- Read the tickets linked to each open bug
- Search Zendesk for similar complaints by hand
- Check satisfaction ratings ticket by ticket
- Prioritise fixes by severity alone
With PopdockAI
- Linked Zendesk tickets are counted for each open bug
- Related tickets for serious bugs are found and marked as judgment
- Bad satisfaction ratings are noted
- The three fixes that would save support most are named, nothing changed
The prompt
Use this prompt
Copy it into any AI tool connected to PopdockAI. Swap the values in braces for your own.
**Objective:** Rank the open bugs in the BugHerd project `{project-name}` by the support load they caused in Zendesk over the last `{lookback-days}` days (default 30).
How the two systems are linked: a BugHerd task created from a Zendesk ticket carries "zendesk:<ticket id>" in its external-id, and the ticket gets a private note naming the task. When a ticket is raised from a BugHerd task, the task gets a comment naming the ticket.
**Step 1: Read the open bugs**
Call `bugherd-get-projects` with `name.contains` set to `{project-name}`. If nothing matches, say so and stop. If several match, list their names and project-id values and ask which one; do not guess. Then call `bugherd-get-tasks` with `project-id` and `max-records` 500. Drop done and closed tasks.
**Step 2: Count tickets per bug**
* Linked: a task with external-id "zendesk:<id>" counts that ticket.
* Related: for each critical or important task, pick two or three distinctive words from its title and call `zendesk-get-ticket` with `subject.contains` for each and `created.from` set to the start of the period. Count tickets that clearly describe the same problem; say these are matched by judgment.
* For counted tickets, also note the satisfaction score when there is one (`zendesk-get-satisfaction-rating` with `ticket-id`).
**Step 3: Report**
A table ordered by ticket count: task number, title, severity, linked tickets, related tickets, bad satisfaction ratings, oldest ticket. Then the three fixes that would save support the most, one sentence each.
**Rules & Guidelines:**
* Tools named bugherd-... are on the bugherd MCP server; tools named zendesk-... are on the zendesk MCP server. If either set of tools is missing, say which server is not connected and stop.
* This prompt is read-only. Do not call any BugHerd write tool (`bugherd-add-task`, `bugherd-add-feedback`, `bugherd-update-task`, `bugherd-move-task`, `bugherd-add-comment`, `bugherd-add-attachment-from-url`, `bugherd-add-project`, `bugherd-update-project`, `bugherd-add-project-member`, `bugherd-add-guest-to-project`) or any Zendesk write tool (`zendesk-add-ticket`, `zendesk-update-ticket`, `zendesk-add-ticket-comment`, `zendesk-make-ticket-comment-private`, `zendesk-add-user`, `zendesk-update-user`, `zendesk-add-organization`, `zendesk-update-organization`, `zendesk-add-organization-member`, `zendesk-add-group`, `zendesk-update-group`, `zendesk-add-group-member`).
**Validation:**
* If no bug has any ticket, say so: support is not seeing these bugs.Who it's for
One answer, three teams that use it
Product managers
Prioritise by customer impact
Rank open bugs by the tickets they generate, so the backlog reflects what customers feel.
Rank open bugs in the Contoso Portal BugHerd project by Zendesk tickets over the last 30 days.
Support managers
Make the case for a fix
Show the dev team which bugs drive the most tickets and bad ratings.
Which Fabrikam Shop BugHerd bugs caused the most Zendesk tickets and bad ratings this quarter?
Engineering managers
Pick fixes that cut ticket volume
Use the top three fixes to plan the sprint around support load.
What are the three Northwind Traders site bugs that would save support the most if fixed?
How it works
What PopdockAI does when you ask
You name the BugHerd project and a period, and your AI assistant weighs each open bug by its Zendesk load. It only reads both systems.
01
Ask
You name the BugHerd project and a period.
02
Read
It reads the open bugs and the Zendesk tickets already linked to them.
03
Match
For critical and important bugs it finds related tickets by subject and notes satisfaction ratings.
04
Report
You get a ranked table and the three fixes that would save support most, with nothing changed.
What PopdockAI provides
The tools behind the answer
Ready made tools for BugHerd and one secure connection to your AI tool. No code, no exports.
bugherd-get-projects
bugherd-get-tasks
zendesk-get-ticket
zendesk-get-satisfaction-rating
This report is built from Get data tools only. PopdockAI applies the row, field and parameter rules your admin sets, and every query is written to the audit trail.
The outcome
Fix the bugs that cost support the most
Related use cases
More ways to put this data to work
One prompt template with infinite possibilities.
Your AI assistant adapts its approach, tone, and capabilities to match each unique context while you maintain a single, manageable workflow.
Join forward-thinking companies that are transforming their operations with intelligent, secure AI automation.

.webp)
