Skip to main content
Prompts are the questions you want to examine in AI responses. They define the situations in which you want to understand whether your brand appears, which other brands are mentioned, and how the answer presents them. A prompt is more than a topic or keyword. It should express a question someone in your audience might actually ask.

How AI Models Interpret Prompts

To understand your AI visibility, it is important to understand how AI models process prompts. Unlike traditional search engines, AI assistants do not focus on individual keywords. They analyze the entire request to understand what the user wants to achieve and which information is relevant to the situation. When someone asks an AI tool a question, the model generally tries to identify three things:

1. The goal

The model first interprets what the user is trying to accomplish. For example: Which project management software is best for remote teams? The goal is to receive recommendations. Compare that to: How can remote teams stay organized? The topic is similar, but the goal is different. The user is looking for advice rather than products. Because the goal differs, the AI may generate entirely different answers.

2. The context

Next, the model analyzes the details surrounding the request. Consider these prompts:
  • What is the best CRM?
  • What is the best CRM for a startup with a small sales team?
The second prompt contains additional context. That context influences which products, features, and recommendations the AI considers relevant. Context often includes:
  • Company size
  • Industry
  • User role
  • Budget constraints
  • Team structure
  • Specific use cases
Even small pieces of context can significantly change the resulting answer.

3. The audience

AI models also infer who is asking the question. A marketing leader, a software developer, and a procurement manager may ask about the same topic in different ways and receive different recommendations. For example: Which analytics platform is best for marketing teams? and Which analytics platform provides the most flexible API integrations? Both prompts concern analytics software, but represent different audiences with different priorities. This is why prompt design and personas work best together. A strong prompt becomes even more valuable when viewed through a specific audience perspective.

Why small wording changes rarely matter

Many users create multiple prompts that ask the same question in slightly different ways. For example:
  • What is the best project management software for remote teams?
  • Which project management platform should a remote team use?
  • What project management tool works best for distributed teams?
Although the wording differs, the intent and context are nearly identical. Modern AI models are generally able to recognize that these prompts represent the same underlying need. As a result, they often produce similar recommendations. Instead of creating many variations of the same question, focus on covering different situations, audiences, and buying stages.

What makes a good visibility prompt?

A useful prompt represents a real decision, challenge, or question that someone in your target audience might have. Good prompts usually:
  • Reflect a genuine user need
  • Include enough context to produce meaningful recommendations
  • Represent a specific audience or use case
  • Help you understand how AI responds in an important business situation
Examples:
  • Which payroll solutions work well for companies with employees across Europe?
  • What cybersecurity tools should medium-sized businesses evaluate in 2026?
  • Which observability platform is easiest for engineering teams to implement?

Common mistakes

Using keywords instead of questions

AI assistants interact through conversations, not keywords. Less useful: CRM software More useful: Which CRM software is best for a growing B2B sales team?

Being too broad

Broad prompts often generate broad answers. Less useful: What is the best marketing software? More useful: Which marketing automation platform is best for SaaS companies with small teams?

Creating duplicate prompts

Different wording does not always create different insights. Instead of adding similar variations, create prompts that represent different audiences, needs, or decision contexts.

Forcing your brand into every prompt

A prompt should help you understand visibility, not artificially create it. Questions that include your brand can be useful for understanding brand perception. However, questions that do not mention your brand are often more valuable for understanding whether AI recommends your brand naturally.

Organize your prompts with Topics

Topics help you organize related prompts into meaningful categories. Each prompt can be attached to multiple topics, making it easier to manage your prompt library and understand performance across different areas of your business. Rather than reviewing prompts one by one, Topics allow you to analyze visibility, sentiment, share of voice, and position across entire topics. Examples of common topics include:
  • Competitor Comparisons
    Questions that compare brands, products, or services within your market.
  • Pricing & Budget Considerations
    Questions about costs, pricing models, ROI, and budget-friendly alternatives.
  • Industry Use Cases
    Questions focused on how solutions are used within specific industries or business contexts.
  • Product Features
    Questions about capabilities, functionality, integrations, and technical requirements.
  • Customer Challenges
    Questions centered around common problems, pain points, and business needs.

Creating your first Topics

When getting started, create a small set of Topics that represent the most important areas where you want to measure AI visibility. You create them on the Topics page; how that works is described in Topics. Starting with a small number of well-defined Topics helps keep your setup organized from the beginning and makes it easier to identify strengths, weaknesses, and opportunities within specific areas of your market.

Creating your first Personas

When getting started, create a small set of Personas that represent your most important customer groups.
  1. Identify your target audiences
    Consider who researches, evaluates, purchases, or uses your solution.
  2. Define their goals and priorities
    Think about what each audience is trying to achieve and what influences their decisions.
  3. Create Personas based on meaningful differences
    Focus on audiences that are likely to ask different questions or have different requirements.
  4. Assign relevant prompts to each Persona
    This helps you analyze how AI responses vary across audiences and customer journeys.
Starting with a few clearly defined Personas makes it easier to build a structured prompt strategy and uncover audience-specific visibility insights.

Option 1: Add Personas manually

Create Manually Persona
  • Click Add Persona in the personas page.
  • Enter a persona name or a short describing naming to distinguish personas from each other.
  • Enter a clear and detailed description of the persona.
  • Click Add Persona to add to your persona library.

Option 2: Generate Personas by AI

Add Personas Generated By Ai
  • Click Add Persona in the personas page.
  • Click the Generate tab.
  • Enter a clear and detailed context of the personas that you want to create or leave it out and let the AI create persona suggestions that are bound to your products and to your company.
  • Select a language.
  • Review the generated personas and select the ones that you want to include into your persona library.
  • Click Add Selection to add to persona library.

Building Your Prompt Library

Your prompt library defines the conversations you want to monitor across AI platforms. A well-structured library helps you understand how AI discusses your brand, competitors, products, and industry from different perspectives. Whether you start with a handful of prompts or hundreds, the goal is the same: track the questions that matter most to your business.

Add Prompts

The Add Prompt dialog on the prompts page has three tabs, one for each way to add prompts:
  • Add: type prompts yourself
  • Bulk upload: upload a file
  • Generate: let AI suggest prompts
Option 1: Add prompts manually
Add Prompt Manually
  • Click Add Prompt on the prompts page. The Add tab opens.
  • Enter your prompts, one per line. Each line becomes its own prompt and is sent to every selected model.
  • Each prompt can be up to 250 characters. A longer line is marked, and you shorten it before you add the prompts.
  • If your plan limits the number of prompts, the counter below the field shows how many you can still add. More lines than that are not added until you remove some.
  • Set Persona. You can choose one persona. It groups and filters your results and is not sent to the models.
  • Set Topics (optional).
  • Set Country, the market of these prompts. Browser-run models ask from this country; API models ignore it.
  • Set Language, the language the models answer in.
  • Set Models. Each model answers every prompt, so more models mean more runs.
  • Click Add Prompt. These prompts run as soon as you add them.
Option 2: Bulk upload Upload many prompts at once as an Excel (.xlsx) or CSV file.
  • Click Add Prompt on the prompts page and open the Bulk upload tab.
  • Click Excel Template to download a template for this project. Its persona and topics cells suggest your project’s personas and topics.
  • Add one prompt per row, then upload the file: drop it on the upload area or click the area to choose it.
  • Set Country and Models. Both are required.
  • Set Language, the language the models answer in.
  • Click Add to Drafts. The prompts appear in the Drafts tab and do not run yet.
Your file needs a header row. Columns are matched by their header, in any order:
  • prompt (required): the prompt text, up to 250 characters. Rows without a prompt are skipped. A longer prompt is marked in Drafts, and you shorten it before you activate it.
  • persona (optional): the name of an existing persona. If the name is not one of your personas, the prompt arrives in Drafts without a persona, and you assign one before you activate it.
  • topics (optional): one or more topic names. Separate several topics with |, or put each further topic in its own cell to the right of the topics column. Topics that do not exist yet are created when you activate the prompts.
Other columns are ignored. A file holds up to 500 prompts. A CSV file can use commas or semicolons to separate its columns. Option 3: Generated prompts by AI Creating prompts from scratch can be challenging, especially when entering a new market or exploring unfamiliar customer journeys. AI-assisted prompt generation helps identify relevant questions based on your business, products, industry, and target audiences. Generated prompts should be treated as starting points rather than final selections. Review each suggestion and focus on questions that represent meaningful customer needs, purchasing decisions, industry challenges, or competitive comparisons. The best prompt libraries combine AI-generated inspiration with domain expertise.
Generate Prompts
  • Click Add Prompt on the prompts page and open the Generate tab.
  • Set Persona. You can choose one persona per generation; the prompts are written from its view.
  • Set Topics the prompts should focus on (optional).
  • Set Country, the country the prompts are localized for.
  • Set Language, the language the prompts are written in.
  • Set Models, the models the prompts run on once activated.
  • Set the Count of prompts to generate.
  • Add Additional context to steer the result (optional).
  • Click Generate. The prompts appear in the Drafts tab.

Review your drafts

Prompts from a bulk upload or from generation wait in the Drafts tab. They do not run until you activate them.
  • Open a draft’s actions menu and choose Edit to change it, for example to assign a missing persona.
  • Select drafts and click Activate to add them to your active prompts, or Reject to drop them.
Drafts come from one source at a time. If you generate prompts while uploaded drafts are waiting, or upload while generated drafts are waiting, you are asked before the waiting drafts are replaced. Drafts are kept in your current browser tab until you activate or reject them.

Prompt System

Your prompts live in three tabs on the prompts page:
  • Active: prompts that are tracked. They run on your selected models and count toward your plan’s prompt limit.
  • Archived: prompts that no longer run but keep their history. They do not count toward your plan’s prompt limit, so archiving a prompt frees its place. Open an archived prompt’s actions menu and choose Activate to move it back to Active and track it again. Activating needs a free place in your plan’s prompt limit and in the project’s prompt allocation.
  • Drafts: prompts from a bulk upload or from generation that you have not activated yet. They do not run and do not count toward your limit until you activate them.

Change, archive and delete prompts

Every prompt row on the prompts page has an actions menu (⋯) at its end. To act on several prompts at once, tick their boxes: a bar with the actions for them appears at the bottom of the page.

Edit a prompt

On the Active tab, open a prompt’s actions menu and choose Edit. The Edit Prompt dialog changes two things:
  • Persona: choose another persona. Changing it archives this prompt, with its history, and starts a new version that is measured from zero.
  • Topics: add or remove topics. Changing only the topics updates this prompt in place, and its history stays with it.
Click Save. The text of a prompt cannot be changed, and neither can its models, country or language: its measurements are of exactly this wording. To ask a different question, add it as a new prompt and archive the old one. While a prompt is still in Drafts, its text can be edited. Without a plan, changing the persona is locked; changing the topics stays possible.

Archive prompts

  • One prompt: open its actions menu on the Active tab and choose Archive.
  • Several prompts: tick them on the Active tab and click Archive in the bar at the bottom.
Archiving stops all future runs. The history and the metrics are kept, and an archived prompt no longer counts toward your plan’s prompt limit. To track it again, open it on the Archived tab and choose Activate, or tick several there and click Activate.

Delete prompts

Open a prompt’s actions menu, on the Active or the Archived tab, and choose Delete. To delete several, tick them and click Delete in the bar at the bottom. Deleting cannot be undone: all historical runs, metrics and analytics of the prompt are removed. It takes a moment; until it is done, the prompt waits on the Archived tab and shows that it is being deleted.

Who can do what

A Viewer sees the prompts and their results, without the actions.

Expand Over Time

Your first prompt set does not need to be perfect. Start with the most important use cases, products, audiences, and competitors. As you collect results, you’ll discover areas where additional prompts can provide deeper insights. Review your prompt library regularly and ask:
  • Which customer questions are already covered?
  • Which audiences are missing?
  • Which competitors appear frequently?
  • Which topics require deeper analysis?
  • Are some prompts producing nearly identical results?
Expanding your library gradually often leads to a more structured and valuable monitoring setup than trying to create hundreds of prompts on day one.