/
/
Catch Ghost Inspector failures nobody has ticketed in Jira
For QA and development teams who want test failures and the Jira bug backlog to agree, by asking their AI assistant to cross-check them.
On this page
Connector
Connect Ghost Inspector, pick your AI tool and paste the prompt.
The problem
Test failures nobody has ticketed
Failures pile up in Ghost Inspector while Jira tracks only some of them. Working out which are untracked, and which open bugs are for tests that now pass, means checking every failing test name against the backlog.
Without PopdockAI
- List recent failures in Ghost Inspector
- Search Jira for each test name
- Check open bugs against current results
- Miss failures and keep stale bugs open
With PopdockAI
- Recent failures are grouped by test so repeats count once
- Each is checked against open Jira bugs, retrying shorter fragments
- Open bugs whose test now passes are found
- Nothing is created or changed in either system
The prompt
Use this prompt
Copy it into any AI tool connected to PopdockAI. Swap the values in braces for your own.
**Objective:** Reconcile recent Ghost Inspector test failures against the bug backlog in Jira project {jira-project-key}, looking back {lookback-days} days (default 14), and report which failures nobody has raised a ticket for. This prompt reports only. It creates and changes nothing.
**Step 1: Collect the failures**
Call `ghost-inspector-get-test-result` on the ghost-inspector server with `passing` set to false and `date-created.from` set to the start of the lookback window. If {suite-name} was supplied, also filter on `suite-name`. Set `max-records` to 200.
Group the results by test name. For each distinct test, keep the most recent failing result: its id, browser, suite and creation date. A test that failed nine times is one problem, not nine.
**Step 2: Look for a ticket on the other side**
For each distinct failing test name, call `jira-get-issue` on the jira server with `project-key` set to {jira-project-key} and `summary.contains` set to the test name. Set `max-records` to 50.
Treat the test as tracked if any returned issue has a status that is not Done, Closed or Resolved. Record that issue's key and status.
If the test name is long or contains punctuation, retry `summary.contains` with a distinctive fragment of it before concluding there is no ticket. A false "untracked" reading is the expensive error here.
**Step 3: Look the other way**
Call `jira-get-issue` again with `project-key` set to {jira-project-key} and `summary.contains` set to `Ghost Inspector failure`. For each open issue returned, take the test name from its summary and check whether that test appears in the Step 1 failure list. An open issue whose test is not currently failing is a close-out candidate.
**Step 4: Report**
Produce three sections.
Untracked failures, as a table: test name, suite, browser, most recent failure date, number of failures in the window, Ghost Inspector result id.
Tracked failures, as a table: test name, Jira issue key, Jira status, most recent failure date.
Close-out candidates, as a table: Jira issue key, summary, status, and a note that the test has not failed within the window.
Finish with one line giving the counts in each section.
**Rules & Guidelines:**
* `ghost-inspector-get-test-result` is on the ghost-inspector server. `jira-get-issue` and `jira-get-project` are on the jira server. All three servers must be connected for this prompt to run.
* The linking convention used by every prompt on this server: a Jira issue raised from a Ghost Inspector failure has a summary beginning `Ghost Inspector failure: ` followed by the test name, and its first comment contains the line `Ghost Inspector result id: ` followed by the result id. Matching in both directions depends on this, so do not vary the wording.
* Do NOT call any write tool. Specifically do not call `jira-add-issue`, `jira-add-issue-comment`, `jira-update-issue`, `jira-assign-issue`, `ghost-inspector-execute-test`, `ghost-inspector-add-test-result-comment` or `ghost-inspector-accept-screenshot`. Raising the tickets is a separate prompt and a separate decision.
**Validation:**
* If `ghost-inspector-get-test-result` returns nothing, report that no test failed in the window and stop. Do not widen the window on your own.
* If `jira-get-issue` returns nothing for every test, say so explicitly rather than reporting every failure as untracked without qualification, because an empty result can also mean the project key is wrong. Confirm the project key exists by calling `jira-get-project` with `project-key` set to {jira-project-key}.
* If a test name matches more than one open issue, list all the keys rather than picking one.Who it's for
One answer, three teams that use it
QA leads
Find failures with no bug
Untracked failures are listed, so you can file the ones that matter.
Which Ghost Inspector failures this week have no open bug in the APP Jira project?
Engineering managers
Close bugs whose tests pass
Open bugs whose test now passes are listed as candidates to close.
Which open bugs in the WEB Jira project are for Ghost Inspector tests that now pass?
Developers
Check one suite against the backlog
Limit the check to one suite to see if your area's failures are tracked.
For the Checkout suite, which Ghost Inspector failures in the last 30 days are missing from the SHOP Jira project?
How it works
What PopdockAI does when you ask
You name the Jira project and a period, and your AI assistant compares failures with the backlog. If Jira returns nothing at all it checks the project key first.
01
Ask
You name the Jira project, a lookback period and optionally a suite.
02
Collect
It groups recent Ghost Inspector failures by test so repeats count once.
03
Match
It searches open Jira bugs for each test, and finds bugs whose test now passes.
04
Report
You get untracked failures and stale bugs, and nothing is created.
What PopdockAI provides
The tools behind the answer
Ready made tools for Ghost Inspector and one secure connection to your AI tool. No code, no exports.
ghost-inspector-get-test-result
jira-get-issue
jira-get-project
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
Nothing falls between testing and the backlog
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)
