Setting up your prompts

Prompts are the foundation of everything Meridian 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 topics and tags, and handle prompts at scale using our 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 ChatGPT, Claude, and Perplexity 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”

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 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 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, Meridian 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 topics work

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 tool.
• “Security” — prompts comparing fraud protection, security features, and safety measures across financial services.

​

Setting up your first topics

Start with 5-10 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.​

​

Create your prompts

There are three ways to add prompts to your project, depending on your workflow and scale.

Navigate to Analytics -> Prompts in your sidebar to get started.

​

Option 1: Add prompts manually

Add prompts individually using the manual input method.

• Click Add Prompts > Add Prompt in the top-right of the Prompts page.
• Enter your prompt.
• Add Topic and custom Attributes (optional).
• Click Add Prompt to save.

Read more about creating topics and tagging prompts.

​

​Option 2: Add Topic (Auto-generate prompts)

Add prompts in batches using the Add Topic method. Our suggestion engine creates prompts based on the topic choosen. How it works:

• Click Add Prompts > Add Topic in the top-right of the Prompts page.
• Enter your topic (think short, SEO-style keyword).
• Toggle the auto-generation feature.
• Click Add Topic to save.

Added prompts will immediately start running. Initial results will be displayed in 15-30 minutes.

​

Option 3: Bulk CSV upload

Upload multiple prompts at once using a structured CSV file. How to upload:

• Click Add Prompt and select Upload CSV.
• Click ‘Choose a CSV File…’ and pick your file.
• Uploads must have two columns: ‘prompt’ and ‘topic’
• Imported prompts appear in Prompts tab and start running immediately.

Your CSV file should be comma- or semicolon-separated with this structure:

• Row 1: Header row with columns ‘prompt’ and ‘topic’.
• Column 1: Prompt text (one per row).
• Column 2: Topic text (one per row).
• Columns 3+: Tags to assign to each prompt:​

​

Manage prompt limits

Your plan includes a specific number of active prompts. You can see it at the top of your Prompts page. You can always upgrade your prompt limit. To do so, book a call with our team and we’ll get you set up!