/
/
Put the explanation on a failed Ghost Inspector suite run
For QA and development teams who want a known failure explained on the run itself, by asking their AI assistant to add the note.
On this page
Connector
Connect Ghost Inspector, pick your AI tool and paste the prompt.
The problem
The reason a run failed lives in a chat thread
When a Ghost Inspector suite fails for a known reason, the explanation usually sits in a chat thread or someone's head instead of on the run. The next person investigates it again, or two people leave conflicting notes.
Without PopdockAI
- Explain the failure in a team chat
- Leave the run itself with no note
- Watch someone else investigate the same failure
- End up with conflicting comments on one run
With PopdockAI
- The most recent failed run is found, never a passing one
- Existing comments are read, and it stops if your point is made
- You see the run, its failed tests and the exact text first
- Your note is posted once, as written, after you confirm
The prompt
Use this prompt
Copy it into any AI tool connected to PopdockAI. Swap the values in braces for your own.
**Objective:** Attach the explanation `{message}` to the most recent failed run of the Ghost Inspector suite named `{suite-name}`, within the last `{lookback-days}` days (default 7), so the failure is on the record.
**Step 1: Identify the suite**
Call `ghost-inspector-get-suite` with `name.contains` set to `{suite-name}`. If more than one matches, list them with their organization and folder and stop. Keep the `id`.
**Step 2: Find the run to annotate**
Call `ghost-inspector-get-suite-result` with `suite-id` from step 1, `passing` false and `date-created.from` at the start of the window. Take the most recent. Keep its `id`, that is the suite result id the comment attaches to. If there are no failed runs in the window, say so and stop; do not comment on a passing run.
**Step 3: Check nobody has already explained it**
Call `ghost-inspector-get-suite-result-comment` with `suite-result-id` from step 2. If a comment already says substantially the same thing as `{message}`, quote it, say the run is already annotated and stop without writing. If there are comments but they say something different, quote them and carry on.
**Step 4: Summarise what actually failed**
Call `ghost-inspector-get-test-result` with the `suite-id` from step 1, `passing` false and a `date-created.from` at the start of that suite run, so you can name the tests that failed within it.
**Step 5: Confirm, then write once**
Show the user the suite, the run date, its pass and fail counts, the tests that failed, and the exact comment text you will post. Ask for confirmation. On an explicit yes, call `ghost-inspector-add-suite-result-comment` with `suite-result-id` from step 2 and `message` set to `{message}`. Call it exactly once.
**Step 6: Report**
Confirm the comment was added, and restate which run it landed on with its date and fail count.
**Rules and guidelines:**
* `ghost-inspector-add-suite-result-comment` is the ONLY tool here that may write, once, after the confirmation in step 5.
* Do NOT call `ghost-inspector-cancel-suite-run`, `ghost-inspector-execute-suite`, `ghost-inspector-execute-test`, `ghost-inspector-update-suite` or any create or duplicate tool.
* Post `{message}` as the user wrote it. Do not rewrite or embellish it; put your own findings in the report to the user instead.
**Validation:**
* If `{suite-name}` matches nothing, list some suite names and stop.
* If `{message}` is empty, ask for the explanation text and stop.
* If the user declines the confirmation, stop without writing.
Who it's for
One answer, three teams that use it
QA engineers
Put the explanation where people look
Your note lands on the failed run itself, so the next person sees it before investigating.
Note on the latest failed Login suite run in Ghost Inspector: staging SSO was down for maintenance.
Developers
Mark a failure as not a product bug
Record that a failure came from an outside cause, so nobody files a bug for it.
Comment on the last failed Search suite run that failures came from the search index rebuild, not a code change.
QA leads
Avoid duplicate or conflicting notes
Existing comments are checked first, so the team keeps one clear explanation per run.
Add a note to the most recent failed Nightly regression run that the CDN outage caused it, unless someone already said so.
How it works
What PopdockAI does when you ask
You name the suite and give your explanation, and your AI assistant finds the right failed run. Nothing is posted until you have seen the exact comment and said yes.
01
Ask
You name the suite and give your explanation.
02
Find
It picks the most recent failed run in the window, never a passing one.
03
Check
It reads existing comments and stops if your point is already made.
04
Confirm
You see the run, its failed tests and the exact text, and it posts once on your yes.
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-suite
ghost-inspector-get-suite-result
ghost-inspector-get-suite-result-comment
ghost-inspector-get-test-result
ghost-inspector-add-suite-result-comment
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
Every known failure explained on the record
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)
