Prompt Diagnosis
Prompt Diagnosis checks every active prompt in your brand at once and tells you what to do with each one: keep tracking it, fix it, or drop it. It answers “is my prompt set actually worth monitoring?” - before you spend monitor runs on prompts that can never show you anything.
What it checks
Every active prompt is scored 0-100 on three signals and matched against the rest of your set for duplicates:
| Signal | What it means | Flagged when |
|---|---|---|
| Clarity | Can an AI tell exactly what you’re asking? Vague prompts return noise | below 40 |
| Topic relevance | Does the prompt fit the topic it’s filed under? | below 40 |
| Commercial value | How likely an AI answer to this prompt names brands or vendors at all. A prompt with no buying intent can never reveal your visibility | below 40 |
| Search demand | Estimated monthly searches, matched from your own Google Search Console / Bing Webmaster queries | below 20/month |
| Duplication | Word-for-word matches, plus near-duplicates by semantic similarity | exact match, or similarity ≥ 0.95 |
Search demand needs a connector. With no connector - or no query that matched the prompt - the volume shows as n/a, never as 0, and the prompt is never flagged for low demand on missing data.
Running a diagnosis
- Go to Configuration → Prompt Management (the page is titled Prompt Topics).
- Open the ⋯ menu in the top right. Under Prompt Diagnosis Options, click Run diagnosis. The run starts in the background - you can leave the page.
- When it finishes, GrackerAI generates prompt suggestions for the intents you’re thin on, then notifies you that the report is ready.
- Come back to the same menu and click View diagnosis report. It always opens your latest report.
While a run is in flight the menu item is disabled and shows the phase - Running diagnosis…, then Finishing…. Both phases must complete before the report opens: the prompts are analysed first, then the suggestions are generated.
To run it again, click Re-run diagnosis in the same menu or at the top of the report. The new run replaces the previous report; older reports are not kept.
Reading the report
The report page is titled Prompt Diagnosis. Back to Prompt Management at the top takes you back. Two tiles sit at the top: Prompts checked and Need attention. Below them, two tabs.
Need Attention
Flagged prompts, grouped by the problem, in this order:
| Group | Why it’s flagged | What to do |
|---|---|---|
| Vague | Unclear or underspecified - an AI can’t tell what you’re asking | Rewrite with the specifics (segment, use case, constraint) |
| Off-topic | Doesn’t fit the topic it’s filed under | Move to topic, or archive |
| Non commercial | No buying intent - the person isn’t comparing, choosing, or buying a product | Archive, or rewrite it toward a purchase decision |
| Low demand | Very low monthly search volume - hardly anyone asks this | Archive, or keep it if it’s strategically important to you |
| Duplicates | Overlaps a prompt you already track, so it double-counts | Archive it - the confirm dialog names the prompt it duplicates |
A prompt appears in exactly one group. Duplicates and hard rejects go straight to their group; anything else that trips more than one borderline bar is filed under the most damaging one first - non commercial, then low demand, then vague, then off-topic.
Groups start collapsed - click one to open its table. A group with no prompts in it isn’t shown at all, so an empty Off-topic section means nothing is filed under the wrong topic. If nothing is flagged, the tab says No prompts need attention.
Each row shows the prompt and a Reason. Off-topic rows also show the Topic, Non commercial rows the Commercial score, and Low demand rows the Volume. The icons on each row:
| Icon | What it does |
|---|---|
| Archive prompt | Archives the prompt after you confirm |
| Move to topic | Re-files the prompt under another topic |
| Add task | Sends the row to Tasks |
Prompts that pass every check are not listed; they are just counted in Prompts checked.
Suggested Prompts
New prompts GrackerAI generated to fill the intents your set is thin on, each with its search demand where known. Add opens the add-prompt form with the text, intent, and suggested topic filled in; you can change them before saving. Once added, the suggestion leaves the list. Add task sends it to Tasks instead.
Acting on the results
Every verdict is advisory. Nothing is archived, merged, or added automatically - archiving always asks you to confirm first, and the dialog repeats the prompt text and the reason.
| Verdict | Confirm dialog | Effect |
|---|---|---|
| Duplicate | Archive this duplicate prompt? | Archives this prompt; the one it duplicates keeps running |
| Not recommended | Archive this prompt? | Archives the prompt - excluded from monitor runs and analytics |
Prompt Management doesn’t show archived prompts. To restore one, open the Prompts page at /org/brand/prompts, set the status filter to Archived, and restore it there.
Limits & gotchas
- A brand run checks up to 500 active prompts. Past that the report shows a Partial badge and says how many were checked.
- Thresholds are deliberately conservative - a rejection tells you to delete your own work, so borderline prompts surface for a look rather than a hard reject.
- A missing signal never counts against a prompt.
n/ameans “we couldn’t measure this”, not “zero”. - The report renders from the run’s stored snapshot. Editing prompts afterwards doesn’t change it - re-run the diagnosis to see the effect.
- Runs from before the current report format may show counts without per-prompt rows. Click Re-run diagnosis to rebuild the full table.
Where Prompt Diagnosis fits
Prompt Diagnosis is the health check on the input to everything else. A weak prompt set makes every downstream score less meaningful.
- Building the set? Prompt Mining creates prompts; Prompt Diagnosis grades what you ended up with.
- Set is clean? Then a low Visibility Score is a real content problem - take a losing prompt into Visibility Diagnosis.
- Reorganising? Off-topic flags are the fastest way to sort prompts into the right topics.
