Prompts

A prompt is a question someone might type into an AI chatbot, written the way they would actually type it. Trakkr reports who gets recommended across eight tracked AI models for your active questions.

That makes the prompt the unit everything else is built on. Your visibility score, your competitor comparisons, your citations, and your audiences all come from the answers these questions produce. Open Prompts when you want to change what Trakkr measures.

What a prompt is

No keywords, no operators, no syntax. Just the question a person asks when they are choosing what to use.

Open category and buyer questions make the clearest visibility baseline: the model has to choose which brands to recommend. The tracking collection asks for a ranked list of brands for the question, rather than reproducing a full consumer chat. Trakkr can also collect branded questions and apply the same position scoring to them, so choose the prompt set with that behavior in mind.

How Trakkr runs your prompts

Active brands receive scheduled daily reports across the tracked models. Check the report date and each model's available results before comparing scores. A completed report does not guarantee a usable result from every provider.

• ChatGPT
• Claude
• Gemini
• Perplexity
• AI Overviews
• Grok
• Meta AI
• DeepSeek

Trakkr records the ranked brands in the collected results and sources where the provider returns them. Your position determines visibility; sentiment is a separate measurement. On Scale and Enterprise you can force an extra run with Rerun report in the header, twice a day per brand.

The Prompts page

Three tabs sit under the page title.

The rest of this page covers the Prompts tab. Tags and Audiences have their own pages.

The header

Add opens a two-item menu: Add prompts or Suggest prompts. Export downloads the rows currently on screen as CSV, and Rerun report appears for Scale and Enterprise; when both are available they collapse into a "···" menu beside Add. Market wording sets how prompts read in each market, and a location filter appears once a brand tracks more than one.

Filter and Display

Filter decides which rows show: status (All, Active, Inactive), AI volume (10K+, 1-10K, under 1K), tags, and audiences. Picking two tags matches prompts with either one, not both.

Display decides how the rows read, and holds the view presets:

The same menu groups rows by tag, audience, or intent, sets the sort, and toggles columns. The search box also reads plain language: "declining", "inactive", and "score above 50" all narrow the list.

The columns

Right-click a header to sort it, hide that column, reset its width, or open the full column list. Drag a column edge to resize.

Health

The Health chip in the header carries a score out of 100 and a band: Strong, Good, Fair, or Needs work. Open it for the full review, which names what your set does well, which prompts to prune, which to add, and the specific problems it found (duplicates, branded prompts, questions too narrow to produce a list). It needs a paid plan and at least three prompts, and it recomputes when your set changes.

Adding prompts

Add → Add prompts opens a staging table. Type one prompt and press Enter, or paste a list and every line lands at once. Upload CSV takes a .csv, .txt, or .tsv up to 2 MB. Tags go after a pipe or a tab, so Best CRM for startups | pricing | discovery creates the prompt with two tags, and two columns pasted from a spreadsheet work the same way. Nothing is written until you commit, rows you already track are marked, and you can stage up to 500 at a time.

Add → Suggest prompts expands the Ideas row at the bottom of the table, where Trakkr proposes prompts as greyed-out ghost rows. It has three modes: your brand name (category questions built from your industry, description, and site), any tag name (more prompts like the ones already carrying it), and a Topic box where you type a feature, use case, or pain point and press Go. Hover a suggestion to see why it was proposed. + adds one, the X dismisses one, and the circular arrow regenerates the list. Nothing counts against your limit until you add it.

When you need more than a handful, use Research instead. It works through hundreds of questions in your market at once, ranked by demand and already carrying position and competitor data.

Writing prompts that matter

Choose useful prompts

You have a fixed number of active slots, so the question is which answers you most need to know.

The best ones come from questions customers already ask. Support tickets, sales call notes, your FAQ page, Search Console queries, community forums, and review sites all beat a brainstorm, because the wording is real.

Cover the range, from scoping the category to naming a hard requirement.

There is a sweet spot between too broad and too narrow. Too broad ("running shoes") and you compete with everyone, so the score never moves. Too narrow ("best running shoes for a flat-footed 38-year-old training a first sub-3 marathon") and nobody asks it, so there is no signal. "Best running shoes for marathon training" is the middle that moves.

Keep research questions separate from the discovery baseline. A branded comparison or how-to may be useful to investigate, but does not make the same test of unaided recommendations. Avoid wording that does not match any real buyer need.

Use this short selection pass:

1. 1.List the buyer questions from sales, support or search data that lead to a purchase.
2. 2.Choose a few category, use-case and requirement questions. Write each in the language and market you want to measure.
3. 3.Put branded research questions in a separate tag, if you need them. Use the tag filter when reading the discovery baseline.
4. 4.Open Add → Add prompts, stage the questions and review duplicates before saving. Check that On is enabled.
5. 5.Read the first usable results for each model. Keep useful zero-scoring questions: removing them would hide the gap.
6. 6.Keep the set stable for comparisons. Record additions, wording edits and deactivations because they change what the score measures.

Near-duplicates are another trap. Tracking "best running shoes", "what are the best running shoes", and "which running shoes are best" spends three slots on one question. Pick one and let Phrasings handle the variants.

Phrasings

Rankings move with wording. "Best CRM for startups" and "What CRM should a startup use" can return different brands, even though a person reads them as the same question. A single prompt cannot see that.

Phrasings generates five variants of a prompt and ranks each one. Run it from Analyze phrasings in the row menu, or by hovering the Score cell. It needs a paid plan.

Each variant shows its position: strong at #1 to #5, weaker at #6 or #7, dark at #8 or absent. A dark phrasing gets two actions. Track adds it as its own prompt. Diagnose opens it in Diagnose to find out why the model skipped you.

The prompt page

Clicking a row opens that prompt's own page. It carries the score with its trend chart, how each model answered, the sources behind those answers, the phrasing variants, and a rail with the prompt's details, its Search Console numbers, and its recent activity.

J and K (or the arrow keys) walk the same filtered order you left the table in. E edits, Space pauses or resumes, and Esc returns to the list.

Editing, pausing, and removing

Double-click the prompt text to edit in place. Edit details in the row menu opens the fuller editor with text, tags, and market together.

The On toggle is the one that matters most. An active prompt is included in scheduled tracking and uses a slot. An inactive prompt is left out of future tracking, gives the slot back, and keeps everything it has collected. Use it for seasonal prompts, for experiments you want to revisit, and for anything you would rather not lose.

A prompt's market

A prompt runs in every market you track unless you give it a market of its own. Choose one under Market in the editor to ask that prompt in one place only:

• If you track that market, the prompt runs and reports there, using that market's wording.
• If you don't, it runs with your primary market's results, asked from the country you chose, exactly as written.

Every model gets the prompt's country, not your primary market's. In the table the prompt shows its flag, and a market that doesn't ask it shows no score for it.

Bulk actions and keyboard shortcuts

Click checkboxes to select. Shift-click extends a range, Cmd or Ctrl click adds one, and the header checkbox takes everything the filters currently show. The bar at the bottom carries Tag, Activate, Deactivate, Archive, and Delete. Right-click the selection for the rest, which is Duplicate all and Move to audience.

Shortcuts stay quiet while you are typing in a field or a dialog is open.

Plan limits

Growth and Scale normally include 50 active prompts per brand. Inactive prompts do not use active slots. Add-ons and managed accounts can change the allowance; use the limit shown on your Prompts page for your account.

Enterprise caps are set in the contract.

Common questions

How many prompts should I start with?

Five to ten. That is enough to see a real pattern without drowning the analysis, and you can add more once you have a baseline to compare against.

Should any prompt mention my brand?

You can track a branded question, and Trakkr can score its ranked results. Keep it separate from your category discovery baseline because naming a brand changes the test. Use tags to compare like with like. Use Perception to research how AI describes your brand, rather than expecting a tracking prompt to return a full narrative review.

How often do prompts run?

Active brands receive scheduled daily reports. Read the latest report date and per-model coverage on the page. Eligible Scale and Enterprise brands can request up to two extra reports per day with Rerun report; the control shows remaining availability.

Why is my score different on each model?

Each model has different training data, different retrieval, and different habits, so ChatGPT may name you often while Perplexity rarely does. That spread is the point of testing all eight, and the per-model breakdown sits on each prompt's own page.

Can I import prompts from a spreadsheet?

Yes. Add → Add prompts takes a pasted list or an uploaded .csv, .txt, or .tsv up to 2 MB, with tags after a pipe or a tab. Up to 500 rows can be reviewed before anything is created.

What happens when I delete a prompt?

The prompt and its tags are removed. The five-second undo recreates the text as a new prompt, not its history, so switch a prompt off rather than removing it if you might want it back.

Can I share one prompt list across brands?

Each brand keeps its own list, because the right phrasing usually differs by brand. To start a second brand from the same set, use Duplicate brand in Brands, which copies the prompts and optionally their tags.