Connectors

/

BugHerd

/

Retest a BugHerd bug with Ghost Inspector
Write
Cross-Connector

Retest BugHerd bugs with Ghost Inspector and close them

For QA and development teams who want a reported bug retested by its covering Ghost Inspector tests, just by asking their AI assistant.

Try PopdockAI free
Get a live demo
Retest a BugHerd bug with Ghost Inspector
Retest BugHerd task 92 in the Northwind Store project with Ghost Inspector.
Both Ghost Inspector tests covering /checkout passed, so task 92 looks fixed. - Guest checkout: passed in 48 seconds - Apply coupon: passed in 35 seconds - Proposed change: set task 92 to done - Proposed comment: Retested with Ghost Inspector: Guest checkout and Apply coupon passed on 2026-10-08. Shall I update the task?
BugHerd
Sample figures. Your results come from your own account.
bugherd-get-projects
bugherd-get-tasks
ghost-inspector-get-test
ghost-inspector-execute-test
bugherd-update-task
bugherd-add-comment
ghost-inspector-get-test-step

On this page

The problem

The problem

The prompt

Who it's for

How it works

Tools used

Connector

BugHerd

BugHerd
Run it on your own BugHerd data.

Connect BugHerd, pick your AI tool and paste the prompt.

Try PopdockAI free

The problem

Fixed bugs sit open or get closed without proof

When a developer says a bug is fixed, someone has to find the Ghost Inspector tests for that page, run them and then close the BugHerd task with a note. Without that, tasks sit open for days or get closed without proof.

Without PopdockAI

  • Find the tests that cover the task's page
  • Run them and read the results
  • Go back to BugHerd to close the task
  • Close it without evidence when time is short

With PopdockAI

  • Tests are found from the task or its page
  • They run only after you confirm
  • Failures report the failed step and leave the task alone
  • Passing tasks are closed with a comment after a second yes

The prompt

Use this prompt

Copy it into any AI tool connected to PopdockAI. Swap the values in braces for your own.

Prompt
**Objective:** Check whether task `{task-number}` in the BugHerd project `{project-name}` is fixed by running the Ghost Inspector tests that cover its page, and close it if they pass and the user agrees.

**Step 1: Read the task**

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 `task-number`. If it is not found, stop. Note its page, external-id and status.

**Step 2: Find the covering tests**

* If the external-id is "ghost-inspector:<test id>", that test covers it: call `ghost-inspector-get-test` with `id`.
* Otherwise call `ghost-inspector-get-test` with `max-records` 500 and keep tests whose start-url matches the task's page. Match pages by URL: compare host and path, ignoring the scheme, a leading "www.", a trailing slash, the query string and the fragment. A BugHerd project matches a Ghost Inspector suite when the suite start-url is on the project development-url host or one of its sites.
* If no test covers the page, say so and stop: this bug needs a manual retest.

**Step 3: Run them**

List the tests you will run and wait for an explicit yes. Then call `ghost-inspector-execute-test` once per test with `test-id` (and `immediate` false so the call waits for the result). Collect passing and execution-time.

**Step 4: Close the task if it passed**

If every test passed, propose: status done, and the comment "Retested with Ghost Inspector: <test names> passed on <date>." Wait for an explicit yes, then call `bugherd-update-task` once with `project-id`, `task-id` and `status` done, and `bugherd-add-comment` once.

If any test failed, call `ghost-inspector-get-test-step` with the new result's id and `passing` false and report the failed step; do not change the task.

**Step 5: Report**

Each test with its result, and what was changed in BugHerd.

**Rules & Guidelines:**

* Tools named bugherd-... are on the bugherd MCP server; tools named ghost-inspector-... are on the ghost-inspector MCP server. If either set of tools is missing, say which server is not connected and stop.
* The only write tools this prompt may call are `ghost-inspector-execute-test` (after the first confirmation), and `bugherd-update-task` and `bugherd-add-comment` (after the second).
* A passing test proves only what it checks; say so if the task describes something the test does not cover.

**Validation:**

* If a test run errors rather than failing, report it as inconclusive and leave the task alone.

Who it's for

One answer, three teams that use it

QA engineers

Retest fixes in one message

Run the right tests for a fixed bug and close it with proof, without switching tools.

Retest BugHerd task 61 in the Contoso Portal project with Ghost Inspector and close it if it passes.

Developers

Prove your fix works

Show the tests passed before the task is closed, so nobody reopens it later.

Run the Ghost Inspector tests for task 208 in the Fabrikam Shop BugHerd project.

Project managers

Close tasks with confidence

Closed tasks carry the test names and date, so you can tell the client it is verified.

Check task 33 in the Northwind Traders site project with Ghost Inspector before I tell the client it is fixed.

How it works

What PopdockAI does when you ask

You name the BugHerd task and your AI assistant finds and runs the Ghost Inspector tests that cover it. It asks before running tests and again before closing the task.

01

Find

It reads the BugHerd task and finds the Ghost Inspector tests that cover its page.

Your AI tool

02

Confirm

You see the tests it will run and say yes.

No items found.

03

Run

It runs each test and reports the result, with the failed step for any failure.

ghost-inspector-execute-test
ghost-inspector-get-test-step

04

Close

If all pass, it proposes marking the task done with a comment and waits for your yes.

Your AI tool

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.

get-data

bugherd-get-projects

Returns BugHerd projects with their website, owner, visibility and status. Filter by project ID, name, owner or active status.
get-data

bugherd-get-tasks

Returns tasks from BugHerd projects: title, description, status, severity, assignee, requester, page, tags, due date and external ID. Filter by project, task number, title, status, severity, assignee, requester email, external ID and due or created date.
get-data

ghost-inspector-get-test

Returns the browser tests defined in Ghost Inspector, with the suite they belong to, their schedule and run settings, and whether the last run passed. Filter by suite, name, browser, region, creation date or current pass state, or fetch a single test by its Ghost Inspector ID.
run-action

ghost-inspector-execute-test

Runs a single Ghost Inspector test and reports whether it passed. The browser, region and start URL can be overridden for the one run, which is how you try a test against staging without editing it. Runs take a while, so set the immediate parameter to return as soon as the run is queued rather than waiting for the result.
run-action

bugherd-update-task

Changes a BugHerd task severity, status (board column) or assignee, recording who made the change.
run-action

bugherd-add-comment

Adds a comment to a BugHerd task, as a given user or email, optionally private to the team.
get-data

ghost-inspector-get-test-step

Returns the individual steps executed within a Ghost Inspector test run, in sequence, with the command, the target element and whether the step passed. Pass a test result ID to see that run's steps. Filter to failing steps only, or to a single command such as click or assign, to find exactly where a test broke.
Read only.Nothing in BugHerd Changes

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.

How Popdock AI secures your data

The outcome

Fixed tasks closed with test evidence

Try PopdockAI free
Get a live demo

Related use cases

More ways to put this data to work

All Ramp use cases

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.

Try PopdockAI Free
See Documentation