Skip to main content

​
Our in-depth guide to building your prompt and competitor tracking system

Prompts are the foundation of everything Orvi AI tracks. This section shows you how to create, organize, and manage prompts for meaningful visibility insights. You’ll learn to understand how AI models work, create effective questions, organize systematically with Brand Topics and tags, and handle prompts at scale using our AI suggestion engine. By the end of it, you’ll build a comprehensive tracking system that captures your visibility across AI platforms.

​
How Prompts Work

Understanding how prompts work with AI models is essential for effective visibility tracking. This section covers how AI models interpret your questions and what that means for your tracking strategy.

​
The Difference Between Prompts and Keywords

Traditional SEO focuses on keywords. AI search requires understanding how people actually converse with AI models. Keyword approach: “Best CRM software.” Prompt approach: “What CRM would work best for a sales team of 10 people?” Key differences:
  • Prompts are longer and conversational.
  • Prompts include context and constraints, not just topics.
  • Prompts use natural language patterns.
Understanding these fundamentals helps you create effective prompts that capture genuine user conversations with AI models.

​
How AI Models Process Prompts

AI models like GPT-5 Chat, Claude Sonnet, Gemini Pro, and Perplexity Sonar don’t match keywords like traditional search engines. They analyze the entire prompt to understand three key things:
  1. Intent recognition: What you’re actually asking for.
  2. Context analysis: The specific situation or constraints mentioned.
  3. Response generation: Crafting an answer that matches both intent and context.
Different intents lead to different responses, but similar intents produce consistent results over time, even when worded differently. For example:
  • “What’s the best CRM?” vs “What’s the best email tool?” → Different intents → Different responses.
  • “What’s the best CRM?” vs “Which CRM should I choose?” → Same intent, different wording → Similar responses.
This means you don’t need multiple variations of the same question. AI models recognize similar intents regardless of exact wording.

​
The Anatomy of an Effective Prompt

Every prompt contains two key components that determine how AI models respond:
  1. Intent: The main ask.
  2. Context: The specifics.
The intent is the core request — what you want the AI to do or answer. This drives the response. Examples of clear intent:
  • “What’s the best…” (seeking recommendations)
  • “How do I…” (seeking instructions)
  • “Compare…” (seeking analysis)
Context provides constraints or situation details that shape how the AI fulfills the intent. Types of context:
  • Audience: “for small businesses,” “for beginners”
  • Use case: “for remote teams,” “for e-commerce”
  • Constraints: “under $100,” “with less than 50 employees”
Prompt example: “What’s the best project management tool for creative agencies with remote teams under 20 people?”
  • Intent: “What’s the best project management tool” (the main ask).
  • Context: “for creative agencies with remote teams under 20 people” (the specifics).
What this means for your tracking:
  • Exact wording doesn’t matter much. Semantically similar prompts will lead to very similar results over time. Focus on capturing the right intent and context rather than perfecting every word.
  • Informational prompts need brand context. For prompts seeking instructions (“How do I…”), AI models likely won’t mention brands unless you specifically ask for them. Add context like “what tools should I use” or “which platforms work best” to get brand mentions in your tracking.

​
Prepare Your Brand Topics

Think in clusters of related prompts rather than individual questions for better suggestions and organization. Before diving into individual prompt creation, consider organizing your tracking around Brand Topics. Topics help you think systematically about the different areas where you want visibility, and they unlock better prompt suggestions from our AI engine. When you create topics first, Orvi AI can generate more targeted prompt suggestions based on those specific themes. Instead of generic suggestions, you’ll get prompts tailored to your exact focus areas.

​
How Brand Topics Work

Brand Topics create folder-like structures where each prompt belongs to exactly one topic. Think of them as containers for related prompts around specific themes or product areas. Examples of effective topics:
  • “Marketing Analytics” — prompts comparing tracking tools, attribution models, and reporting platforms.
  • “AI Writing” — prompts about content generation, editing assistance, and writing workflows.
  • “Remote Collaboration” — prompts comparing video conferencing, project management, and team communication tools.
  • “Security” — prompts comparing fraud protection, security features, and safety measures across financial services.

​
Setting Up Your First Topics

Start with 3–5 broad areas where you want to track AI visibility:
  1. Identify your key product areas: What are the main categories where you want to appear?
  2. Create topics for each area: Use clear, specific names that reflect those categories.
  3. Request topic-based suggestions: Generate prompts tailored to each topic area.
  4. Expand with manual prompts: Add specific prompts that suggestions might miss.
You can always create additional topics later, but starting with topic-based thinking helps you build a more organized and effective prompt strategy from day one. Topics also make analysis easier down the line — you can track visibility at the topic level instead of individual prompts in your Overview dashboard.

​
Create Your Prompts

There are three ways to add prompts to your project, depending on your workflow and scale. Navigate to Prompts in your sidebar to get started.

​
Option 1: Use Prompt Suggestions

Our AI suggestion engine creates prompts based on your website, industry context, existing prompts in your project, and competitors. How it works:
  1. Go to the Suggested tab in the Prompts / Brand section and review generated suggestions.
  2. Click Track to move prompts to your Active tab (you’ll select which topic to add them to).
  3. If you don’t see suggestions, click Suggest prompts to create new ones.
  4. Click Suggest more to generate additional suggestions. If you’ve reached the limit of 10 suggested prompts, reject a few unsuitable ones and click the button again.
Accepted prompts are added to your Active prompts (in the selected topic) and start running immediately, joining the regular daily execution cycle. Note: Suggested prompts don’t count toward your plan limit until you track them. You can have up to 10 suggested prompts at a time.

​
Option 2: Add Prompts Manually

Add prompts individually using the manual input method.
  1. Click Add Prompt in the top-right of the Prompts page.
  2. Enter your prompt (max 200 characters).
  3. Set Location to choose which country to run the prompt from (this determines the language and regional context).
  4. Select a Topic (for brand prompts) or leave as “No topic”.
  5. Add Tags (optional) to organize prompts across topics.
  6. Click Add to save.
The Location setting determines the geographic location where your prompt runs. Different locations can produce different AI responses based on regional content preferences and availability. Available locations: United States, Canada, United Kingdom, France, Germany, Italy, Spain, Netherlands, Belgium, Sweden, Poland, Austria, Switzerland, Portugal, Denmark, Norway, Finland, Ireland, Mexico. If your desired country isn’t available, contact us and we’ll add it in the next update.

​
Option 3: Product Prompts (Separate Type)

Product Prompts are a separate type of prompt designed to track product-level recommendations. They work similarly to brand prompts but:
  • They’re organized in a flat list (not grouped by topics).
  • They track which products AI models recommend (discovered dynamically from responses).
  • They help you understand product-level visibility, sentiment, and position.
To add product prompts:
  1. Navigate to Prompts / Product.
  2. Use the same methods: Suggest prompts, Add manually, or manage existing prompts.
  3. Product prompts also support location, tags, and status (active/inactive).

​
Brand Prompts vs Product Prompts

Orvi AI supports two types of prompts, each serving different tracking goals:

​
Brand Prompts

  • Purpose: Track how your brand (and competitors) appears in category-level conversations.
  • Organization: Grouped into Brand Topics (e.g., “CRM Tools”, “Email Marketing”).
  • What they track: Brand mentions, visibility, sentiment, and position for predefined brands.
  • Use case: Understanding brand-level AI visibility and competitive positioning.

​
Product Prompts

  • Purpose: Track which products AI models recommend when users ask product-specific questions.
  • Organization: Flat list (no topics).
  • What they track: Product mentions (discovered dynamically), visibility, sentiment, and position.
  • Use case: Understanding product-level recommendations and which URLs/sources support them.
Both types use the same prompt structure (text, location, tags, status) but serve different analytical purposes.

​
Organize with Tags

Tags help you organize prompts across topics and projects. They’re optional but useful for:
  • Cross-topic organization: Tag prompts with “High Priority”, “Q4 Campaign”, etc.
  • Filtering and analysis: Filter analytics by tag combinations.
  • Project management: Track which prompts belong to specific initiatives.
To add tags:
  1. Create tags in your project settings or when adding/editing prompts.
  2. Assign tags to prompts during creation or editing.
  3. Use tags to filter analytics in your dashboards.
Tags are stored at the project level and can be reused across all prompts (both brand and product).

​
Manage Prompt Status

Your prompts can be in one of three states:

​
Active Prompts

  • Count toward your plan limit and run daily.
  • Generate visibility data and appear in analytics.
  • Shown in the Active tab.

​
Inactive Prompts

  • Don’t count toward limits but preserve historical data.
  • You can always reactivate them from your Inactive tab.
  • Useful for temporarily pausing prompts without losing data.

​
Suggested Prompts

  • Don’t count until you track them.
  • Temporary storage (max 10 for brand prompts, separate limit for product prompts).
  • Review and either Track (move to Active) or Reject (remove).
This system lets you experiment with new prompts while staying within your plan by deactivating less important ones rather than deleting them entirely.

​
Prompt Limits

Your plan includes a specific number of active prompts (combining both brand and product prompts). You can see your limit and current usage at the top of your Prompts page. How limits work:
  • Active prompts: Count toward your plan limit and run daily.
  • Inactive prompts: Don’t count toward limits but preserve historical data.
  • Suggested prompts: Don’t count until you track them.
Managing limits:
  • If you reach your limit, deactivate some prompts to free up slots.
  • Upgrade your plan to increase your active prompt limit.
  • Use tags and topics to organize and prioritize your most important prompts.

​
Best Practices

​
Creating Effective Prompts

  1. Be conversational: Write prompts as real users would ask AI.
  2. Include context: Add audience, use case, or constraints to get more relevant results.
  3. Focus on intent: Don’t worry about perfect wording — similar intents produce similar results.
  4. Avoid brand names: Generic prompts test if AI naturally recommends your brand.
  5. Keep it under 200 characters: Concise prompts work best.

​
Organizing Your System

  1. Start with topics: Create 3–5 broad topics before adding prompts.
  2. Use suggestions: Let AI generate initial prompts, then refine manually.
  3. Tag strategically: Use tags for campaigns, priorities, or cross-cutting themes.
  4. Review regularly: Deactivate low-performing prompts and double down on winners.

​
Scaling Your Tracking

  1. Prioritize by impact: Focus on prompts that drive the most visibility.
  2. Monitor performance: Use analytics to see which prompts generate the best results.
  3. Iterate based on data: Adjust prompts based on what you learn from AI responses.
  4. Stay within limits: Use inactive status to manage your prompt portfolio without losing data.

​
What’s Next?

Once your prompts are set up and running:
  1. Monitor your results: Check your Overview dashboard to see visibility, sentiment, and position metrics.
  2. Analyze by topic: Use topic filters to understand which areas drive the most visibility.
  3. Review sources: See which domains and URLs influence AI responses in your Sources views.
  4. Refine your strategy: Use data to identify high-performing prompts and optimize your tracking system.
For more advanced strategies, see our guides on interpreting results and taking action.
Last modified on January 25, 2026